[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79D0J36ZGVRD0H6FJ32A0GG":3,"skill-same:01M79D0J36ZGVRD0H6FJ32A0GG":93},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M79D0J36ZGVRD0H6FJ32A0GG","boltz-protein-design",null,"Design new protein binders with Boltz. Use when generating protein, peptide, antibody, nanobody, or custom binder candidates for a target. Not for screening existing proteins or small molecules.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: boltz-protein-design\ndescription: Design new protein binders with Boltz. Use when generating protein, peptide, antibody, nanobody, or custom binder candidates for a target. Not for screening existing proteins or small molecules.\n---\n\n## Workflow\n\nIf `boltz-api` is missing from `PATH`, use `boltz-cli-setup` for install\u002Fupdate guidance before retrying.\nIf a command reports missing or expired authentication, use `boltz-cli-setup` to start `boltz-api auth login --device-code` before retrying; do not ask permission first.\nIf the agent host sandbox blocks `boltz-api` install\u002Fauth\u002FAPI calls, use `boltz-cli-setup` to request the host sandbox bypass\u002Fescalation needed for user-wide CLI install, browser login, credential storage, temp files, or API access before retrying.\n\nUse this skill when the user wants de novo protein \u002F peptide \u002F antibody \u002F nanobody binders.\n\n1. **Decide on target exploration first (new targets).** For a new target where the user hasn't already fixed the binding site and crop, your first action — before authoring a payload, normalizing the target, or running `estimate-cost` — is to raise the choice between a target-exploration pass and designing directly, with a **recommendation** for this target:\n   - Unknown site, or a multi-domain \u002F large target → recommend exploration (it scouts different input configurations for generation, ≈50 designs each, and finds the best before a full run).\n   - A well-characterized site → it's fine to recommend going (mostly) direct, perhaps with a quick check of whether conditioning on the epitope beats letting the model find its own spot. State this plainly, as part of a conversation with the user about their target and goals, and let them choose.\n\n   Phrase it as a question that works *with* the user (they may know their target's biology), e.g.:\n\n   > \"This is a fresh target — I'd suggest a quick exploration pass that scouts a few framings and picks the best before a full run. Or, if you already know the site and crop, we can design directly. Which would you like?\"\n\n   **Do not mention a campaign size or tier here** — not even folded into this opening approach question. The full-run size is settled later, after the scouting runs pick a winner (its yield informs the tier), so don't ask it up front when exploration is on the table. If the user opts into exploration — or has already said they want to explore \u002F let the design find its own epitope — read [references\u002Ftarget-exploration.md](references\u002Ftarget-exploration.md), follow it, then resume at step 8 with the chosen framing and recommended `num_proteins`. If they want to design directly, continue below.\n2. Normalize the target (same shape as protein-screen): `structure_template` if a CIF\u002FPDB is available, else `no_template`.\n3. Pick the `binder_specification` variant. Supported variants include:\n   - `boltz_curated` — recommended default for antibody and nanobody design. Boltz selects from maintained scaffold\u002Ftemplate lists (`binder: boltz_antibody` or `boltz_nanobody`).\n   - `structure_template` — redesign motifs in an existing binder scaffold (CIF + `design_motifs` with `replacement` \u002F `insertion` segments).\n   - `no_template` — generate from the sequence DSL (fixed residues + designed segments like `5..10` or `8`).\n4. For antibody or nanobody requests, ask before authoring the payload: \"I recommend Boltz's curated antibody\u002Fnanobody scaffolds for this. Do you want the curated default, or do you have custom scaffold structures\u002FCDR motifs to use?\" If the user picks curated, use `type: boltz_curated`; if they want custom scaffold control, use `type: structure_template`.\n5. Pick `modality`: `peptide`, `antibody`, `nanobody`, or `custom_protein` for `structure_template` and `no_template` (use `custom_protein` for a \"miniprotein\" or generic \"protein binder\"). **If the user already named the modality, take it as given — don't ask again.** Do not include `modality` on `boltz_curated`; use `binder` instead.\n6. Pick `num_proteins` — see [Run sizing](#run-sizing). Valid range is **10 to 1,000,000** (server rejects outside it); **10** is the hard floor but it is a test size, not a campaign. When the user has not given a count, propose a campaign tier (default **50,000**), not the floor.\n7. Supported optional features include rules such as excluded amino acids, excluded sequence motifs with `X` wildcards, and max hydrophobic fraction. Add `rules` only on request; read [references\u002Fapi.md](references\u002Fapi.md) for exact shapes and examples.\n8. Author the payload YAML or JSON, then run `estimate-cost` and apply the **spending gate** (Always Do This) before `start`. (Cost model — tiered by total complex length, `estimate-cost` is the only source: see [`## Cost`](references\u002Fapi.md) in api.md.)\n9. `start` to submit. Capture the ID.\n10. Launch `download-results` with the agent runtime's background\u002Fnon-blocking command facility. In Claude Code, use Bash with `run_in_background: true`. In Codex, run `download-results` as a foreground shell command with `yield_time_ms: 1000`; if Codex returns a `session_id`, keep it for optional same-thread polling, but treat `download-status` plus the run directory as the durable source of truth. In Codex app\u002Fdesktop runtimes that expose same-thread heartbeat automations, create a heartbeat that checks `download-status` periodically and posts a concise completion or failure update when the download reaches a terminal state. After launching the downloader, always report the job ID, run name, and output directory. Include the next check cadence if the heartbeat was created; otherwise include the `download-status` command.\n11. Rank from `\u003Coutput-root>\u002F\u003Crun-name>\u002Fresults\u002Findex.jsonl` by `binding_confidence` descending. Use `iptm` and `min_interaction_pae` as tiebreakers. `optimization_score` is not emitted for this endpoint. Read [references\u002Fresults.md](references\u002Fresults.md) for output layout and metric details.\n\n## Run sizing\n\nDe novo design is a generate-and-filter campaign: you make many binders and keep the rare good ones, so a real run is **large**. Do not anchor on the `num_proteins` floor of 10 — that is only useful for a quick setup test. When the user names a count, honor it (≥10). When they do not, explain the tiers and propose one:\n\n| Tier | `num_proteins` | When |\n|---|---|---|\n| Small screen | 20,000 | Quick look \u002F tight budget |\n| **Medium (recommended)** | **50,000** | Default for a real campaign |\n| Large | 100,000 | Hard target \u002F maximal coverage |\n\nPresent the tiers as design **counts**, not dollars: don't put a price next to a tier unless `estimate-cost` returned it — run `estimate-cost` on the tier the user leans toward and show that figure, and never extrapolate one estimate across the others. Then apply the **spending gate** (Always Do This) before submitting. If the setup is unproven, suggest a small test run (tens of designs) or the full [target-exploration](references\u002Ftarget-exploration.md) pass first.\n\n## Command Pattern\n\n```bash\n# Replace placeholders with concrete absolute paths before running.\n# Use a short descriptive run name, for example: protein-design-\u003Cmodality>-\u003Ctarget>-v1\n\nboltz-api protein:design estimate-cost \\\n  --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml\n\nboltz-api protein:design start \\\n       --idempotency-key \"\u003Crun-name>\" \\\n       --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml \\\n       --raw-output --transform id\n\n# Copy the printed job ID into this command, then launch it in the agent\n# runtime's background\u002Fnon-blocking mode.\n# Claude Code: Bash with run_in_background=true.\n# Codex: foreground shell command with yield_time_ms=1000; keep the returned session_id if one is provided.\n# Do not append \"&\" or use nohup in Codex.\nboltz-api download-results \\\n  --id \"\u003Cjob-id-from-start>\" --name \"\u003Crun-name>\" \\\n  --root-dir \"\u002Fabsolute\u002Fpath\u002Fboltz-experiments\" \\\n  --poll-interval-seconds 60\n```\n\nPayload keys are `num_proteins`, `target`, `binder_specification` — API body field names.\n\n## Always Do This\n\n- **For a new target, your first move is the step-1 conversation — never jump straight to a payload.** Establish what the binder is *for* and whether the user has already fixed the binding site\u002Fcrop, then recommend a target-exploration pass vs. designing directly and let them choose (step 1). Only normalize the target and author a payload after that. If they've already fixed the site\u002Fcrop or explicitly want to design directly, proceed.\n- Enforce `10 \u003C= num_proteins \u003C= 1,000,000` before calling `estimate-cost` (server rejects outside that range), but 10 is the floor, not a campaign — see [Run sizing](#run-sizing) and propose a tier (default 50,000) when the user gives no count.\n- **Spending gate — explicit go-ahead before every `start`.** `start` spends real money. A plan you already described, an earlier phase's approval, or a cost that looks \"trivial\" are **not** authorization — even a cheap run needs a fresh yes. Run `estimate-cost`, show the `estimated_cost_usd` it returns (summed for a batch), and wait for the user to say go. This holds **even when tool calls are pre-approved** (accept-edits \u002F auto-accept \u002F bypass modes) — there you are the only cost gate. Never quote or assume a dollar figure you didn't get from `estimate-cost` (cost model: [`## Cost`](references\u002Fapi.md) in api.md).\n- For antibody or nanobody design, recommend `binder_specification.type: boltz_curated` and ask the user to confirm they do not want custom scaffold\u002FCDR control before building the payload. Use `binder: boltz_antibody` for antibody\u002FFab requests and `binder: boltz_nanobody` for nanobody\u002FVHH requests.\n- Residue indices are 0-based everywhere (`design_motifs.start_index`\u002F`end_index`, `after_residue_index`, `epitope_residues`, `flexible_residues`, bonds, constraints).\n- For CIF\u002FPDB bytes, use `@data:\u002F\u002F\u002Fabs\u002Fpath\u002Ffile.cif` inside `structure.data`. Don't use bare `@path`.\n- Sequence DSL for `designed_protein.value`: uppercase letters = fixed residues; integer `N` = exactly `N` designed residues; `MIN..MAX` = variable-length designed segment. Examples: `\"20\"`, `\"5..10\"`, `\"ACDE8GHI\"`, `\"MKTAYI5..10VKSHFSRQ\"`.\n- Keep payload field names exactly as the API body names shown in `references\u002Fapi.md`.\n- Use absolute paths for the output root, payload files, and embedded target files. Do not `cd` into the run directory for follow-up commands; pass the same `--root-dir` and use absolute paths so later relative paths do not drift.\n- Prefer one merged top-level payload via `--input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml` or `@json:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.json` for `estimate-cost` and `start`. Keep `--idempotency-key` and `--workspace-id` top-level; if they also appear inside `--input`, the top-level flags win.\n- Direct object flags still work as overrides, such as `--target @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Ftarget.yaml` or `--binder-specification @json:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fbinder.json`. Piped YAML \u002F JSON on stdin also works, but it must use API body field names. Use the same slug for both `--idempotency-key` and `--name`.\n- In permission-gated agents such as Claude Code, keep each Boltz call as a top-level command that starts with `boltz-api`. Prefer concrete arguments over `sh -c`, inline environment assignments, aliases, wrapper scripts, loops, or pipelines around the `boltz-api` invocation unless the user already allowed that exact command form. Use `--raw-output --transform id`, read the printed ID, then paste that literal ID into the next `download-results` command.\n- Prefer the agent runtime's background\u002Fnon-blocking command mode for `download-results`. In Codex specifically, keep `download-results` in the foreground and set the shell tool yield to 1000 ms; Codex will return a `session_id` if the command is still running. Do not append `&` or use `nohup` in Codex because the tool runner may clean up shell-backgrounded descendants before `.boltz-run.json` is fully written.\n- After the background\u002Fsession starts, do not manually wait on it or run ad hoc polling loops. Wall-clock time scales roughly with `num_proteins`: under 100 often finishes in a few minutes, 100-1,000 may take several minutes to tens of minutes, and larger runs can take longer or hours depending on inputs and system load. Don't quote a fixed duration. `--poll-interval-seconds 60` is a sensible downloader default. `download-results` emits JSONL progress on stderr by default; add `--progress-format text --verbose` only when you explicitly want human-readable logs.\n- In Codex app\u002Fdesktop runtimes with same-thread heartbeat automation support, schedule a heartbeat after launching `download-results`. The heartbeat should run `boltz-api --format json download-status --name \"\u003Crun-name>\" --root-dir \"\u002Fabsolute\u002Fpath\u002Fboltz-experiments\"` and stop once terminal. Choose cadence by `num_proteins`: under 100 -> every 1-2 minutes; 100-1,000 -> every 5 minutes; over 1,000 -> every 15 minutes. Post only material status changes or terminal completion\u002Ffailure. Poll the saved `session_id` with an empty `write_stdin` only for interactive, user-requested progress checks. Never run a manual poll loop in the current turn.\n- If the current host has no heartbeat automation support, do not claim an automatic next check. Report the job ID, run name, output directory, and the command needed to check `download-status`.\n- If detached download needs to be restarted, re-run `boltz-api download-results` with the same `--name \"\u003Crun-name>\"` and the same `--root-dir`.\n- Only add `rules` on explicit user request.\n\n## Escape Hatch\n\n- Payload reference: \u003Chttps:\u002F\u002Fapi.boltz.bio\u002Fdocs\u002Fapi\u002Fresources\u002Fprotein\u002Fsubresources\u002Fdesign\u002Fmethods\u002Fstart\u002F>\n- CLI flag names: `boltz-api protein:design start --help`\n\nRead [references\u002Fapi.md](references\u002Fapi.md) for all `binder_specification` variants, motif shapes, sequence DSL, rules, modalities, and `target` variants. Read [references\u002Fresults.md](references\u002Fresults.md) after download when ranking designed binders or explaining outputs.\n\n## Outputs\n\nRank from `results\u002Findex.jsonl` after `download-results`; use [references\u002Fresults.md](references\u002Fresults.md) for local file layout, metric meanings, and the designed-binder entity type gotcha.\n","## Workflow\n\nIf `boltz-api` is missing from `PATH`, use `boltz-cli-setup` for install\u002Fupdate guidance before retrying.\nIf a command reports missing or expired authentication, use `boltz-cli-setup` to start `boltz-api auth login --device-code` before retrying; do not ask permission first.\nIf the agent host sandbox blocks `boltz-api` install\u002Fauth\u002FAPI calls, use `boltz-cli-setup` to request the host sandbox bypass\u002Fescalation needed for user-wide CLI install, browser login, credential storage, temp files, or API access before retrying.\n\nUse this skill when the user wants de novo protein \u002F peptide \u002F antibody \u002F nanobody binders.\n\n1. **Decide on target exploration first (new targets).** For a new target where the user hasn't already fixed the binding site and crop, your first action — before authoring a payload, normalizing the target, or running `estimate-cost` — is to raise the choice between a target-exploration pass and designing directly, with a **recommendation** for this target:\n   - Unknown site, or a multi-domain \u002F large target → recommend exploration (it scouts different input configurations for generation, ≈50 designs each, and finds the best before a full run).\n   - A well-characterized site → it's fine to recommend going (mostly) direct, perhaps with a quick check of whether conditioning on the epitope beats letting the model find its own spot. State this plainly, as part of a conversation with the user about their target and goals, and let them choose.\n\n   Phrase it as a question that works *with* the user (they may know their target's biology), e.g.:\n\n   > \"This is a fresh target — I'd suggest a quick exploration pass that scouts a few framings and picks the best before a full run. Or, if you already know the site and crop, we can design directly. Which would you like?\"\n\n   **Do not mention a campaign size or tier here** — not even folded into this opening approach question. The full-run size is settled later, after the scouting runs pick a winner (its yield informs the tier), so don't ask it up front when exploration is on the table. If the user opts into exploration — or has already said they want to explore \u002F let the design find its own epitope — read [references\u002Ftarget-exploration.md](references\u002Ftarget-exploration.md), follow it, then resume at step 8 with the chosen framing and recommended `num_proteins`. If they want to design directly, continue below.\n2. Normalize the target (same shape as protein-screen): `structure_template` if a CIF\u002FPDB is available, else `no_template`.\n3. Pick the `binder_specification` variant. Supported variants include:\n   - `boltz_curated` — recommended default for antibody and nanobody design. Boltz selects from maintained scaffold\u002Ftemplate lists (`binder: boltz_antibody` or `boltz_nanobody`).\n   - `structure_template` — redesign motifs in an existing binder scaffold (CIF + `design_motifs` with `replacement` \u002F `insertion` segments).\n   - `no_template` — generate from the sequence DSL (fixed residues + designed segments like `5..10` or `8`).\n4. For antibody or nanobody requests, ask before authoring the payload: \"I recommend Boltz's curated antibody\u002Fnanobody scaffolds for this. Do you want the curated default, or do you have custom scaffold structures\u002FCDR motifs to use?\" If the user picks curated, use `type: boltz_curated`; if they want custom scaffold control, use `type: structure_template`.\n5. Pick `modality`: `peptide`, `antibody`, `nanobody`, or `custom_protein` for `structure_template` and `no_template` (use `custom_protein` for a \"miniprotein\" or generic \"protein binder\"). **If the user already named the modality, take it as given — don't ask again.** Do not include `modality` on `boltz_curated`; use `binder` instead.\n6. Pick `num_proteins` — see [Run sizing](#run-sizing). Valid range is **10 to 1,000,000** (server rejects outside it); **10** is the hard floor but it is a test size, not a campaign. When the user has not given a count, propose a campaign tier (default **50,000**), not the floor.\n7. Supported optional features include rules such as excluded amino acids, excluded sequence motifs with `X` wildcards, and max hydrophobic fraction. Add `rules` only on request; read [references\u002Fapi.md](references\u002Fapi.md) for exact shapes and examples.\n8. Author the payload YAML or JSON, then run `estimate-cost` and apply the **spending gate** (Always Do This) before `start`. (Cost model — tiered by total complex length, `estimate-cost` is the only source: see [`## Cost`](references\u002Fapi.md) in api.md.)\n9. `start` to submit. Capture the ID.\n10. Launch `download-results` with the agent runtime's background\u002Fnon-blocking command facility. In Claude Code, use Bash with `run_in_background: true`. In Codex, run `download-results` as a foreground shell command with `yield_time_ms: 1000`; if Codex returns a `session_id`, keep it for optional same-thread polling, but treat `download-status` plus the run directory as the durable source of truth. In Codex app\u002Fdesktop runtimes that expose same-thread heartbeat automations, create a heartbeat that checks `download-status` periodically and posts a concise completion or failure update when the download reaches a terminal state. After launching the downloader, always report the job ID, run name, and output directory. Include the next check cadence if the heartbeat was created; otherwise include the `download-status` command.\n11. Rank from `\u003Coutput-root>\u002F\u003Crun-name>\u002Fresults\u002Findex.jsonl` by `binding_confidence` descending. Use `iptm` and `min_interaction_pae` as tiebreakers. `optimization_score` is not emitted for this endpoint. Read [references\u002Fresults.md](references\u002Fresults.md) for output layout and metric details.\n\n## Run sizing\n\nDe novo design is a generate-and-filter campaign: you make many binders and keep the rare good ones, so a real run is **large**. Do not anchor on the `num_proteins` floor of 10 — that is only useful for a quick setup test. When the user names a count, honor it (≥10). When they do not, explain the tiers and propose one:\n\n| Tier | `num_proteins` | When |\n|---|---|---|\n| Small screen | 20,000 | Quick look \u002F tight budget |\n| **Medium (recommended)** | **50,000** | Default for a real campaign |\n| Large | 100,000 | Hard target \u002F maximal coverage |\n\nPresent the tiers as design **counts**, not dollars: don't put a price next to a tier unless `estimate-cost` returned it — run `estimate-cost` on the tier the user leans toward and show that figure, and never extrapolate one estimate across the others. Then apply the **spending gate** (Always Do This) before submitting. If the setup is unproven, suggest a small test run (tens of designs) or the full [target-exploration](references\u002Ftarget-exploration.md) pass first.\n\n## Command Pattern\n\n```bash\n# Replace placeholders with concrete absolute paths before running.\n# Use a short descriptive run name, for example: protein-design-\u003Cmodality>-\u003Ctarget>-v1\n\nboltz-api protein:design estimate-cost \\\n  --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml\n\nboltz-api protein:design start \\\n       --idempotency-key \"\u003Crun-name>\" \\\n       --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml \\\n       --raw-output --transform id\n\n# Copy the printed job ID into this command, then launch it in the agent\n# runtime's background\u002Fnon-blocking mode.\n# Claude Code: Bash with run_in_background=true.\n# Codex: foreground shell command with yield_time_ms=1000; keep the returned session_id if one is provided.\n# Do not append \"&\" or use nohup in Codex.\nboltz-api download-results \\\n  --id \"\u003Cjob-id-from-start>\" --name \"\u003Crun-name>\" \\\n  --root-dir \"\u002Fabsolute\u002Fpath\u002Fboltz-experiments\" \\\n  --poll-interval-seconds 60\n```\n\nPayload keys are `num_proteins`, `target`, `binder_specification` — API body field names.\n\n## Always Do This\n\n- **For a new target, your first move is the step-1 conversation — never jump straight to a payload.** Establish what the binder is *for* and whether the user has already fixed the binding site\u002Fcrop, then recommend a target-exploration pass vs. designing directly and let them choose (step 1). Only normalize the target and author a payload after that. If they've already fixed the site\u002Fcrop or explicitly want to design directly, proceed.\n- Enforce `10 \u003C= num_proteins \u003C= 1,000,000` before calling `estimate-cost` (server rejects outside that range), but 10 is the floor, not a campaign — see [Run sizing](#run-sizing) and propose a tier (default 50,000) when the user gives no count.\n- **Spending gate — explicit go-ahead before every `start`.** `start` spends real money. A plan you already described, an earlier phase's approval, or a cost that looks \"trivial\" are **not** authorization — even a cheap run needs a fresh yes. Run `estimate-cost`, show the `estimated_cost_usd` it returns (summed for a batch), and wait for the user to say go. This holds **even when tool calls are pre-approved** (accept-edits \u002F auto-accept \u002F bypass modes) — there you are the only cost gate. Never quote or assume a dollar figure you didn't get from `estimate-cost` (cost model: [`## Cost`](references\u002Fapi.md) in api.md).\n- For antibody or nanobody design, recommend `binder_specification.type: boltz_curated` and ask the user to confirm they do not want custom scaffold\u002FCDR control before building the payload. Use `binder: boltz_antibody` for antibody\u002FFab requests and `binder: boltz_nanobody` for nanobody\u002FVHH requests.\n- Residue indices are 0-based everywhere (`design_motifs.start_index`\u002F`end_index`, `after_residue_index`, `epitope_residues`, `flexible_residues`, bonds, constraints).\n- For CIF\u002FPDB bytes, use `@data:\u002F\u002F\u002Fabs\u002Fpath\u002Ffile.cif` inside `structure.data`. Don't use bare `@path`.\n- Sequence DSL for `designed_protein.value`: uppercase letters = fixed residues; integer `N` = exactly `N` designed residues; `MIN..MAX` = variable-length designed segment. Examples: `\"20\"`, `\"5..10\"`, `\"ACDE8GHI\"`, `\"MKTAYI5..10VKSHFSRQ\"`.\n- Keep payload field names exactly as the API body names shown in `references\u002Fapi.md`.\n- Use absolute paths for the output root, payload files, and embedded target files. Do not `cd` into the run directory for follow-up commands; pass the same `--root-dir` and use absolute paths so later relative paths do not drift.\n- Prefer one merged top-level payload via `--input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml` or `@json:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.json` for `estimate-cost` and `start`. Keep `--idempotency-key` and `--workspace-id` top-level; if they also appear inside `--input`, the top-level flags win.\n- Direct object flags still work as overrides, such as `--target @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Ftarget.yaml` or `--binder-specification @json:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fbinder.json`. Piped YAML \u002F JSON on stdin also works, but it must use API body field names. Use the same slug for both `--idempotency-key` and `--name`.\n- In permission-gated agents such as Claude Code, keep each Boltz call as a top-level command that starts with `boltz-api`. Prefer concrete arguments over `sh -c`, inline environment assignments, aliases, wrapper scripts, loops, or pipelines around the `boltz-api` invocation unless the user already allowed that exact command form. Use `--raw-output --transform id`, read the printed ID, then paste that literal ID into the next `download-results` command.\n- Prefer the agent runtime's background\u002Fnon-blocking command mode for `download-results`. In Codex specifically, keep `download-results` in the foreground and set the shell tool yield to 1000 ms; Codex will return a `session_id` if the command is still running. Do not append `&` or use `nohup` in Codex because the tool runner may clean up shell-backgrounded descendants before `.boltz-run.json` is fully written.\n- After the background\u002Fsession starts, do not manually wait on it or run ad hoc polling loops. Wall-clock time scales roughly with `num_proteins`: under 100 often finishes in a few minutes, 100-1,000 may take several minutes to tens of minutes, and larger runs can take longer or hours depending on inputs and system load. Don't quote a fixed duration. `--poll-interval-seconds 60` is a sensible downloader default. `download-results` emits JSONL progress on stderr by default; add `--progress-format text --verbose` only when you explicitly want human-readable logs.\n- In Codex app\u002Fdesktop runtimes with same-thread heartbeat automation support, schedule a heartbeat after launching `download-results`. The heartbeat should run `boltz-api --format json download-status --name \"\u003Crun-name>\" --root-dir \"\u002Fabsolute\u002Fpath\u002Fboltz-experiments\"` and stop once terminal. Choose cadence by `num_proteins`: under 100 -> every 1-2 minutes; 100-1,000 -> every 5 minutes; over 1,000 -> every 15 minutes. Post only material status changes or terminal completion\u002Ffailure. Poll the saved `session_id` with an empty `write_stdin` only for interactive, user-requested progress checks. Never run a manual poll loop in the current turn.\n- If the current host has no heartbeat automation support, do not claim an automatic next check. Report the job ID, run name, output directory, and the command needed to check `download-status`.\n- If detached download needs to be restarted, re-run `boltz-api download-results` with the same `--name \"\u003Crun-name>\"` and the same `--root-dir`.\n- Only add `rules` on explicit user request.\n\n## Escape Hatch\n\n- Payload reference: \u003Chttps:\u002F\u002Fapi.boltz.bio\u002Fdocs\u002Fapi\u002Fresources\u002Fprotein\u002Fsubresources\u002Fdesign\u002Fmethods\u002Fstart\u002F>\n- CLI flag names: `boltz-api protein:design start --help`\n\nRead [references\u002Fapi.md](references\u002Fapi.md) for all `binder_specification` variants, motif shapes, sequence DSL, rules, modalities, and `target` variants. Read [references\u002Fresults.md](references\u002Fresults.md) after download when ranking designed binders or explaining outputs.\n\n## Outputs\n\nRank from `results\u002Findex.jsonl` after `download-results`; use [references\u002Fresults.md](references\u002Fresults.md) for local file layout, metric meanings, and the designed-binder entity type gotcha.\n",{"name":5,"description":7},"main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fboltz-protein-design","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog","https:\u002F\u002Fgithub.com\u002Fzfifteen","I like to measure things.","2026-07-19 23:41:54",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add zfifteen\u002Fskills-catalog --skill boltz-protein-design",{"tool":37,"command":38},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill boltz-protein-design",{"tool":40,"command":41},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill boltz-protein-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002FSKILL.md",true,[45,51,55,59,63,69,73,77,81,85,89],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",223,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fapi.md",12304,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Freferences\u002Fapi.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fresults.md",1079,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Freferences\u002Fresults.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ftarget-exploration.md",16516,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Freferences\u002Ftarget-exploration.md",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002F_common.py","SCRIPT","脚本",2807,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fscripts\u002F_common.py",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fanalyze_results.py",2481,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fscripts\u002Fanalyze_results.py",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fcrop_radius.py",2857,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fscripts\u002Fcrop_radius.py",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fdetect_disorder.py",3268,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fscripts\u002Fdetect_disorder.py",{"path":82,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Frequirements.txt",227,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fscripts\u002Frequirements.txt",{"path":86,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fscan_sites.py",6488,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fscripts\u002Fscan_sites.py",{"path":90,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fterminus.py",1629,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fboltz-protein-design\u002Fscripts\u002Fterminus.py",[94,101,108,115,124,131],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M79GXQ2PWPT2E4CJYHXVJ0YE","Zotero","Use Zotero Desktop from Codex to enable\u002Fprobe the local API, search a local Zotero library, list items\u002Fcollections\u002Ftags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX\u002FRIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzotero\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M79GXN85NETKBE06865CWK6Z","zoom-apps-sdk","Use when using Apps SDK.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M79GXCYD7FGYS932J9N9RFFY","youtube","Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript.  Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or \"what does this video actually say\".  The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content.  Triggers: \"youtube transcript\", \"get the transcript of this video\", \"summarize this youtube video\", \"what did they say in https:\u002F\u002Fyoutube.com\u002F...\", \"key claims from this talk\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M79GX8EXHHYM566BKR7MS778","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M79GX2HFJPX84NMRE5VBTYX9","x-post-creator","Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, \u002Fx-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs\u002Fx-posts\u002F[story-name]\u002F.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-post-creator\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":19},"01M79GWXQT4HBT6QME6QSBZJFA","x-api","Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X\u002Fx.com, reading threads and replies, creating lists, staging\u002Fpublishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions \u002Fx-api or \"search X\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]