[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSPAWAG44V33E9JR7E2RF1":3,"skill-same:01M7CSPAWAG44V33E9JR7E2RF1":50},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7CSPAWAG44V33E9JR7E2RF1","read-only-security-scanners",null,"Use when you want deterministic evidence for a review - which already-installed scanners may be run against the checkout, their exact read-only invocations, how to triage their output, and what must never be run or installed","makifbaysal\u002Ftasktrooper","makifbaysal","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F25031940?v=4","01M7CRG3ZCSYZSSEVDMW3DEYC8","Mehmet Akif Baysal","01M7CRG401FJ8YAXH5ER730XYV",122,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fsecurity-agent\u002Fskills\u002Fread-only-security-scanners\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: read-only-security-scanners\ncategory: security\ndescription: Use when you want deterministic evidence for a review - which already-installed scanners may be run against the checkout, their exact read-only invocations, how to triage their output, and what must never be run or installed\ntech_stack: Secure review method\nsource: original; informed by trailofbits\u002Fskills (CC BY-SA 4.0, ideas only, own wording); semgrep, gitleaks, TruffleHog, osv-scanner, govulncheck, gosec, Bandit, pip-audit, zizmor, Checkov and Trivy documentation cited, not reproduced\n---\n# Read-Only Security Scanners\n\n## Overview\n\nScanners are fast, deterministic and noisy. They find candidates you might skim past; they also report hundreds of things this review excludes. They never decide the verdict — every hit goes through the false-positive gate like any other candidate, and a clean scan is not a clean review.\n\n**Core principle:** use what is already installed, in a mode that only reads, on the files this diff changed. Never install anything; never run anything from the project.\n\n## 1. First, What Did CI Already Run?\n\n- `get_pipeline_status` — a secret scan, SAST or dependency-audit job may already have reported on this exact commit; its output is in the job result.\n- `list_component_checks` — which security checks exist for the component and whether CI gates on them.\n\nDo not re-run what CI already ran on this commit; triage its output instead. When `semgrep`, `osv-scanner`, `github-security` or `snyk` tools are in your tool list, those MCP servers are connected — security-mcp-scanners covers them; the CLIs below are the fallback.\n\n## 2. Ground Rules\n\n- **Installed only:** `command -v semgrep gitleaks trufflehog osv-scanner govulncheck gosec bandit pip-audit zizmor checkov trivy`. Missing → skip it; it is a coverage note, not a reason to fail the review.\n- **Never install or fetch-and-run:** no `pip install`, `pipx run`, `uvx`, `npx`, `npm i -g`, `go install`, `go run …@latest`, `brew install`, `docker run` of a scanner image.\n- **Never run project code:** no `npm install`\u002F`ci`, no build, no `go generate`, no `make`, no CodeQL database creation for compiled languages (it runs the build) — read CI's CodeQL results instead.\n- **Never modify:** no `--fix`, `--autofix`, `npm audit fix`, `osv-scanner fix`, no scanner baseline written into the repo.\n- **Output goes outside the checkout:** `out=\u002Ftmp\u002Ftt-\u003Ctask key>\u002Fscan; mkdir -p \"$out\"`. Pass `timeout_seconds` for slow tools.\n- **Repo config is input, not authority:** a `.semgrepignore`, `.gitleaks.toml`, `.gitleaksignore`, `nosec`\u002F`# nosemgrep` comment or `.trivyignore` added or widened in this diff is itself something to review.\n\n## 3. Invocations\n\n```sh\nbase=$(git merge-base HEAD origin\u002FHEAD 2>\u002Fdev\u002Fnull || git merge-base HEAD origin\u002Fmain)\nchanged=$(git diff --name-only --diff-filter=AM \"$base\")\n```\n\n| Tool | Purpose | Read-only invocation | Caveat |\n|------|---------|----------------------|--------|\n| semgrep | SAST, many languages | `semgrep scan --metrics=off --config p\u002Fdefault --json -o \"$out\u002Fsemgrep.json\" $changed` | `--config auto` needs metrics — don't; avoid `--baseline-commit`, it manipulates the git working tree; registry configs need network, a repo `.semgrep.yml` works offline |\n| gitleaks | secrets in the diff's commits | `gitleaks git --log-opts=\"$base..HEAD\" --redact --no-banner --report-format json --report-path \"$out\u002Fgitleaks.json\" .` | older v8: `gitleaks detect --log-opts=…`; working tree only: `gitleaks dir \u003Cpath>` \u002F `detect --no-git --source \u003Cpath>` |\n| trufflehog | secrets, broader detectors | `trufflehog git file:\u002F\u002F. --since-commit \"$base\" --no-update --no-verification --json` | verification calls the provider with the found credential — leave that to CI; `--no-update` stops self-update |\n| osv-scanner | advisories for lockfiles | v2: `osv-scanner scan source -L \u003Clockfile> --format json`; v1: `osv-scanner --lockfile=\u003Clockfile> --format json` | reports `MAL-` malicious packages too; never `fix` |\n| govulncheck | Go advisories with reachability | `GOTOOLCHAIN=local GOFLAGS=-mod=readonly govulncheck -json .\u002F...` | loads packages via `go list` (may fill the module cache, never runs project code); `GOTOOLCHAIN=local` stops a `toolchain` line fetching another Go |\n| gosec | Go SAST | `gosec -quiet -fmt=json -out=\"$out\u002Fgosec.json\" .\u002F...` | high noise on G104\u002FG115 — triage hard |\n| bandit | Python SAST | `bandit -q -f json -o \"$out\u002Fbandit.json\" \u003Cchanged .py files>` | flags every `subprocess` import; only trace hits on `+` lines |\n| npm \u002F pnpm audit | JS advisories | `npm audit --package-lock-only --json` · `pnpm audit --json` | reads the lockfile only; no install, no scripts |\n| pip-audit | Python advisories | `pip-audit --no-deps --disable-pip -r requirements.txt -f json` | without both flags it builds a venv and **installs** the requirements, running their setup code; needs pinned requirements |\n| zizmor | GitHub Actions | `zizmor --offline --format json .github\u002Fworkflows\u002F` | `--offline` skips GitHub API audits |\n| checkov | Terraform, k8s, Dockerfiles | `checkov -d \u003Cdir> --compact --quiet -o json` | never enable external module download |\n| trivy | IaC misconfig, secrets, lockfiles | `trivy config \u003Cdir>` · `trivy fs --scanners vuln,secret,misconfig \u003Cdir>` | check `trivy --version` first: v0.69.4 is the malicious release from the March 2026 compromise (CVE-2026-33634) — do not run it, and say so in your run summary |\n\n## 4. Triage\n\nFor each hit:\n\n1. **Is it on the diff?** Keep hits on `+` lines, or on unchanged lines the diff newly routes input into. Drop the rest — pre-existing findings are not this review.\n2. **Is it excluded?** DoS, ReDoS, test files, hardening-only rules, outdated-library-without-advisory → drop (security-hard-exclusions-and-precedents).\n3. **Does it pass the gate?** Restate, trace source → sink, name attacker and victim (false-positive-gate). The scanner's severity is a hint; yours is the one in the comment.\n4. **Deduplicate** across tools; one root cause is one SEC-n.\n5. **Cite the tool** in the evidence line when it found the issue (\"gitleaks: aws-access-token, config\u002Fprod.go:12\"), never paste raw output.\n\n## 5. Failures and Silence\n\n- A scanner that errors, times out or cannot parse a file is a coverage limit — mention it in the summary line; it is neither a pass nor a finding.\n- A scanner that finds nothing has only checked its own rules. Your source → sink reading still decides.\n\n## Common Mistakes\n\n- Pasting a scanner's 40 findings into the comment.\n- Blocking on a scanner \"HIGH\" that is a test fixture, a constant or a pre-existing line.\n- Running `pip-audit -r` without `--no-deps --disable-pip`, or `npx some-scanner` \"just this once\".\n- Treating \"semgrep: 0 findings\" as approval.\n\n## Red Flags\n\n- A command in your plan that installs, builds, or fetches a tool to run it.\n- Scanner output written into the repository checkout.\n- A diff that adds a broad ignore rule to a scanner config next to new code the rule would have flagged.\n- A CI scanner action referenced by tag instead of commit SHA (supply-chain-and-dependency-review).\n\n## References (names and links only)\n\n[Semgrep CLI](https:\u002F\u002Fsemgrep.dev\u002Fdocs\u002Fcli-reference) · [gitleaks](https:\u002F\u002Fgithub.com\u002Fgitleaks\u002Fgitleaks) · [TruffleHog](https:\u002F\u002Fgithub.com\u002Ftrufflesecurity\u002Ftrufflehog) · [osv-scanner](https:\u002F\u002Fgoogle.github.io\u002Fosv-scanner\u002F) · [govulncheck](https:\u002F\u002Fgo.dev\u002Fdoc\u002Fsecurity\u002Fvuln\u002F) · [pip-audit](https:\u002F\u002Fgithub.com\u002Fpypa\u002Fpip-audit) · [zizmor](https:\u002F\u002Fdocs.zizmor.sh\u002F) · [Checkov](https:\u002F\u002Fwww.checkov.io\u002F) · [Trivy](https:\u002F\u002Ftrivy.dev\u002F) · CVE-2026-33634\n","# Read-Only Security Scanners\n\n## Overview\n\nScanners are fast, deterministic and noisy. They find candidates you might skim past; they also report hundreds of things this review excludes. They never decide the verdict — every hit goes through the false-positive gate like any other candidate, and a clean scan is not a clean review.\n\n**Core principle:** use what is already installed, in a mode that only reads, on the files this diff changed. Never install anything; never run anything from the project.\n\n## 1. First, What Did CI Already Run?\n\n- `get_pipeline_status` — a secret scan, SAST or dependency-audit job may already have reported on this exact commit; its output is in the job result.\n- `list_component_checks` — which security checks exist for the component and whether CI gates on them.\n\nDo not re-run what CI already ran on this commit; triage its output instead. When `semgrep`, `osv-scanner`, `github-security` or `snyk` tools are in your tool list, those MCP servers are connected — security-mcp-scanners covers them; the CLIs below are the fallback.\n\n## 2. Ground Rules\n\n- **Installed only:** `command -v semgrep gitleaks trufflehog osv-scanner govulncheck gosec bandit pip-audit zizmor checkov trivy`. Missing → skip it; it is a coverage note, not a reason to fail the review.\n- **Never install or fetch-and-run:** no `pip install`, `pipx run`, `uvx`, `npx`, `npm i -g`, `go install`, `go run …@latest`, `brew install`, `docker run` of a scanner image.\n- **Never run project code:** no `npm install`\u002F`ci`, no build, no `go generate`, no `make`, no CodeQL database creation for compiled languages (it runs the build) — read CI's CodeQL results instead.\n- **Never modify:** no `--fix`, `--autofix`, `npm audit fix`, `osv-scanner fix`, no scanner baseline written into the repo.\n- **Output goes outside the checkout:** `out=\u002Ftmp\u002Ftt-\u003Ctask key>\u002Fscan; mkdir -p \"$out\"`. Pass `timeout_seconds` for slow tools.\n- **Repo config is input, not authority:** a `.semgrepignore`, `.gitleaks.toml`, `.gitleaksignore`, `nosec`\u002F`# nosemgrep` comment or `.trivyignore` added or widened in this diff is itself something to review.\n\n## 3. Invocations\n\n```sh\nbase=$(git merge-base HEAD origin\u002FHEAD 2>\u002Fdev\u002Fnull || git merge-base HEAD origin\u002Fmain)\nchanged=$(git diff --name-only --diff-filter=AM \"$base\")\n```\n\n| Tool | Purpose | Read-only invocation | Caveat |\n|------|---------|----------------------|--------|\n| semgrep | SAST, many languages | `semgrep scan --metrics=off --config p\u002Fdefault --json -o \"$out\u002Fsemgrep.json\" $changed` | `--config auto` needs metrics — don't; avoid `--baseline-commit`, it manipulates the git working tree; registry configs need network, a repo `.semgrep.yml` works offline |\n| gitleaks | secrets in the diff's commits | `gitleaks git --log-opts=\"$base..HEAD\" --redact --no-banner --report-format json --report-path \"$out\u002Fgitleaks.json\" .` | older v8: `gitleaks detect --log-opts=…`; working tree only: `gitleaks dir \u003Cpath>` \u002F `detect --no-git --source \u003Cpath>` |\n| trufflehog | secrets, broader detectors | `trufflehog git file:\u002F\u002F. --since-commit \"$base\" --no-update --no-verification --json` | verification calls the provider with the found credential — leave that to CI; `--no-update` stops self-update |\n| osv-scanner | advisories for lockfiles | v2: `osv-scanner scan source -L \u003Clockfile> --format json`; v1: `osv-scanner --lockfile=\u003Clockfile> --format json` | reports `MAL-` malicious packages too; never `fix` |\n| govulncheck | Go advisories with reachability | `GOTOOLCHAIN=local GOFLAGS=-mod=readonly govulncheck -json .\u002F...` | loads packages via `go list` (may fill the module cache, never runs project code); `GOTOOLCHAIN=local` stops a `toolchain` line fetching another Go |\n| gosec | Go SAST | `gosec -quiet -fmt=json -out=\"$out\u002Fgosec.json\" .\u002F...` | high noise on G104\u002FG115 — triage hard |\n| bandit | Python SAST | `bandit -q -f json -o \"$out\u002Fbandit.json\" \u003Cchanged .py files>` | flags every `subprocess` import; only trace hits on `+` lines |\n| npm \u002F pnpm audit | JS advisories | `npm audit --package-lock-only --json` · `pnpm audit --json` | reads the lockfile only; no install, no scripts |\n| pip-audit | Python advisories | `pip-audit --no-deps --disable-pip -r requirements.txt -f json` | without both flags it builds a venv and **installs** the requirements, running their setup code; needs pinned requirements |\n| zizmor | GitHub Actions | `zizmor --offline --format json .github\u002Fworkflows\u002F` | `--offline` skips GitHub API audits |\n| checkov | Terraform, k8s, Dockerfiles | `checkov -d \u003Cdir> --compact --quiet -o json` | never enable external module download |\n| trivy | IaC misconfig, secrets, lockfiles | `trivy config \u003Cdir>` · `trivy fs --scanners vuln,secret,misconfig \u003Cdir>` | check `trivy --version` first: v0.69.4 is the malicious release from the March 2026 compromise (CVE-2026-33634) — do not run it, and say so in your run summary |\n\n## 4. Triage\n\nFor each hit:\n\n1. **Is it on the diff?** Keep hits on `+` lines, or on unchanged lines the diff newly routes input into. Drop the rest — pre-existing findings are not this review.\n2. **Is it excluded?** DoS, ReDoS, test files, hardening-only rules, outdated-library-without-advisory → drop (security-hard-exclusions-and-precedents).\n3. **Does it pass the gate?** Restate, trace source → sink, name attacker and victim (false-positive-gate). The scanner's severity is a hint; yours is the one in the comment.\n4. **Deduplicate** across tools; one root cause is one SEC-n.\n5. **Cite the tool** in the evidence line when it found the issue (\"gitleaks: aws-access-token, config\u002Fprod.go:12\"), never paste raw output.\n\n## 5. Failures and Silence\n\n- A scanner that errors, times out or cannot parse a file is a coverage limit — mention it in the summary line; it is neither a pass nor a finding.\n- A scanner that finds nothing has only checked its own rules. Your source → sink reading still decides.\n\n## Common Mistakes\n\n- Pasting a scanner's 40 findings into the comment.\n- Blocking on a scanner \"HIGH\" that is a test fixture, a constant or a pre-existing line.\n- Running `pip-audit -r` without `--no-deps --disable-pip`, or `npx some-scanner` \"just this once\".\n- Treating \"semgrep: 0 findings\" as approval.\n\n## Red Flags\n\n- A command in your plan that installs, builds, or fetches a tool to run it.\n- Scanner output written into the repository checkout.\n- A diff that adds a broad ignore rule to a scanner config next to new code the rule would have flagged.\n- A CI scanner action referenced by tag instead of commit SHA (supply-chain-and-dependency-review).\n\n## References (names and links only)\n\n[Semgrep CLI](https:\u002F\u002Fsemgrep.dev\u002Fdocs\u002Fcli-reference) · [gitleaks](https:\u002F\u002Fgithub.com\u002Fgitleaks\u002Fgitleaks) · [TruffleHog](https:\u002F\u002Fgithub.com\u002Ftrufflesecurity\u002Ftrufflehog) · [osv-scanner](https:\u002F\u002Fgoogle.github.io\u002Fosv-scanner\u002F) · [govulncheck](https:\u002F\u002Fgo.dev\u002Fdoc\u002Fsecurity\u002Fvuln\u002F) · [pip-audit](https:\u002F\u002Fgithub.com\u002Fpypa\u002Fpip-audit) · [zizmor](https:\u002F\u002Fdocs.zizmor.sh\u002F) · [Checkov](https:\u002F\u002Fwww.checkov.io\u002F) · [Trivy](https:\u002F\u002Ftrivy.dev\u002F) · CVE-2026-33634\n",{"name":5,"source":24,"category":25,"tech_stack":26,"description":7},"original; informed by trailofbits\u002Fskills (CC BY-SA 4.0, ideas only, own wording); semgrep, gitleaks, TruffleHog, osv-scanner, govulncheck, gosec, Bandit, pip-audit, zizmor, Checkov and Trivy documentation cited, not reproduced","security","Secure review method","main","910394a0b6db9fc8c9a8f36328ec421d3ebd8b38","catalog\u002Fagents\u002Fsecurity-agent\u002Fskills\u002Fread-only-security-scanners",18,"https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper","https:\u002F\u002Ftasktrooper.ai","https:\u002F\u002Fgithub.com\u002Fmakifbaysal","Senior Software Developer","2026-11-15 04:50:29",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add makifbaysal\u002Ftasktrooper --skill read-only-security-scanners",{"tool":42,"command":43},"bunx","bunx skills add makifbaysal\u002Ftasktrooper --skill read-only-security-scanners",{"tool":45,"command":46},"pnpm","pnpm dlx skills add makifbaysal\u002Ftasktrooper --skill read-only-security-scanners","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fsecurity-agent\u002Fskills\u002Fread-only-security-scanners\u002FSKILL.md",true,[],[51,57,64,71,78,85],{"skillNo":52,"name":53,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7CSVEPQW6J6TD6CS2T5FPNZ","visual-craft","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fvisual-craft\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7CSVAQG91ETHQ0HBNZDG5FR","ux-copy","Use when you write any words a user reads in a mockup or a hand-off - content language and voice, buttons, labels, errors, empty states, confirmations, numbers and dates, and the longest-string check","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fux-copy\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CSV6H0J38659NDXHJQ8396","screen-mockup-html","Use when you draw screens as the design task's HTML mockup - ONE canvas document holding every screen and every variant side by side, the sanitizer-safe recipe, phone and wide frames, the states grid, static control states, and the loopback self-check with screenshots at 375, 768 and 1440 attached to the task","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fscreen-mockup-html\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CSV3JFRF3BM3XK52M7YEYR","performance-awareness","How the performance score moves for your role. Use when the score context shows a declining trend, or before handing off work you have not self-checked against every criterion.","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fperformance-awareness\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CSTZDH00YRF5SCT7BRT9QD","design-variants","Use when a screen design needs variants - how many, variants as side-by-side rows on the one canvas, what makes two variants genuinely different, recommending one, how the human's choice is read, and narrowing to the chosen one in revision","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-variants\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CSTV6P3SM3PAE28DB0RF77","design-system-authoring","Use when you derive, change or extend a design system - where tokens live per stack, the DTCG token tree, role-based names for both themes, base vs layer vs drift, the DESIGN.md section order, the inventory format, the contrast check and the lint every proposal returns","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-system-authoring\u002FSKILL.md",[],[]]