longform-practice
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-07-27
- Stars
- ★ 0
- Forks
- 0
02 资源文件 82
- 参考文档.claude/settings.json196 B
- 其他.gitignore34 B
- 脚本engram/__tests__/agents.test.ts2.6 KB
- 脚本engram/__tests__/diff.test.ts2.0 KB
- 脚本engram/__tests__/index.test.ts3.3 KB
- 脚本engram/__tests__/install-type.test.ts838 B
- 脚本engram/__tests__/install.test.ts6.7 KB
- 脚本engram/__tests__/parse-frontmatter.test.ts1.1 KB
- 脚本engram/__tests__/session-start.test.ts4.3 KB
- 脚本engram/__tests__/update-tool.test.ts9.4 KB
- 脚本engram/__tests__/update.test.ts7.6 KB
- 参考文档engram/.agents/plugins/marketplace.json511 B
- 参考文档engram/.claude-plugin/marketplace.json443 B
- 参考文档engram/.claude-plugin/plugin.json504 B
- 参考文档engram/.codex-plugin/plugin.json640 B
- 参考文档engram/.github/workflows/test.yml418 B
- 其他engram/.gitignore58 B
- 其他engram/.nojekyll—
- 其他engram/.opencode/.gitignore53 B
- 脚本engram/.opencode/agents.ts1.9 KB
- 参考文档engram/.opencode/agents/artifact-smith.md37 B
- 参考文档engram/.opencode/agents/assessor.md31 B
- 参考文档engram/.opencode/agents/curriculum-architect.md43 B
- 脚本engram/.opencode/diff.ts4.6 KB
- 脚本engram/.opencode/index.ts15.2 KB
- 脚本engram/.opencode/install-type.ts548 B
- 脚本engram/.opencode/install.ts9.3 KB
- 脚本engram/.opencode/parse-frontmatter.ts652 B
- 脚本engram/.opencode/update-tool.ts8.9 KB
- 脚本engram/.opencode/update.ts8.0 KB
- 参考文档engram/agents/engram-artifact-smith.md3.7 KB
- 参考文档engram/agents/engram-assessor.md4.9 KB
- 参考文档engram/agents/engram-curriculum-architect.md5.1 KB
- 资产文件engram/assets/banner.png858.9 KB
- 参考文档engram/assets/promo-image-spec.md5.1 KB
- 其他engram/bun.lock28.8 KB
- 参考文档engram/CHANGELOG.md108.3 KB
- 其他engram/codex/agents/engram-artifact-smith.toml3.8 KB
- 其他engram/codex/agents/engram-assessor.toml4.5 KB
- 其他engram/codex/agents/engram-curriculum-architect.toml5.4 KB
- 参考文档engram/CONTRIBUTING-DATA.md7.2 KB
- 参考文档engram/docs/01-foundations.md25.1 KB
- 参考文档engram/docs/02-prior-art.md9.8 KB
- 参考文档engram/docs/03-architecture.md16.5 KB
- 参考文档engram/docs/04-roadmap.md7.2 KB
- 参考文档engram/docs/05-affective-layers.md20.0 KB
- 参考文档engram/docs/06-visual-encoding.md17.7 KB
- 参考文档engram/docs/07-the-measured-loop.md31.7 KB
- 参考文档engram/docs/08-vision.md26.4 KB
- 参考文档engram/docs/09-target-architecture.md27.9 KB
- 参考文档engram/docs/10-roadmap-to-1.0.md27.9 KB
- 参考文档engram/docs/release-audits/v0.7.0-numbers-audit.md7.6 KB
- 参考文档engram/docs/user-sessions/v0.6.2.md5.1 KB
- 参考文档engram/docs/user-sessions/v0.7.0-the-existing-user.md5.0 KB
- 参考文档engram/examples/features-as-dimensions.html23.2 KB
- 参考文档engram/examples/pid-error-feedback-loop.html37.7 KB
- 参考文档engram/examples/README.md1.4 KB
- 其他engram/gold/assessor-gold.jsonl76.2 KB
- 参考文档engram/hooks/hooks.json293 B
- 脚本engram/hooks/session-start.sh754 B
- 脚本engram/hooks/session-start.ts3.5 KB
- 脚本engram/hooks/shell-env.ts1.7 KB
- 参考文档engram/INSTALL-CODEX.md4.5 KB
- 许可证engram/LICENSE1.0 KB
- 参考文档engram/package-lock.json60.8 KB
- 参考文档engram/package.json912 B
- 参考文档engram/README.md38.3 KB
- 参考文档engram/RELEASE_PROTOCOL.md43.8 KB
- 脚本engram/scripts/engram.py440.0 KB
- 脚本engram/scripts/install-codex.sh1.6 KB
- 参考文档engram/skills/_shared/dialogue-grammar.md15.4 KB
- 参考文档engram/skills/_shared/explorable-contract.md5.1 KB
- 参考文档engram/tsconfig.json269 B
- 脚本engram/vitest.config.ts119 B
- 参考文档README.md7.8 KB
- 脚本scripts/corpus_index.js8.2 KB
- 脚本scripts/maturity_gate.js3.3 KB
- 脚本scripts/package.json269 B
- 脚本scripts/session_context.js4.2 KB
- 脚本scripts/tests/corpus_index.test.js3.8 KB
- 脚本scripts/tests/maturity_gate.test.js4.5 KB
- 脚本scripts/tests/session_context.test.js5.8 KB
03 SKILL.md 正文
longform-practice
Entry point for starting or continuing a long-form practice session for a
vault concept — as opposed to engram's own /learn <topic>, which
takes an open-ended topic string typed by the learner. This procedure scopes
generation to one 100_concepts//200_execution/ note's confirmed problem
types/cases once its flashcards clear the maturity gate, grounded by any
matched EngiBench exemplars.
This procedure was originally speced out in an internal design doc not
included in this repo — see README.md in this directory for the
summarized design and verification notes.
Design note — engram/ internals are untouched by this procedure.
engram-curriculum-architect already accepts {topic, goal, deadline, prior exposure, interests} and already has Read in its tool list. This skill
doesn't fork or replace it — it changes only what gets fed into it: the
topic/goal are constrained to a note's already-confirmed problem
types/cases instead of an open string, and the note content + matched
exemplars are attached as grounding. Everything downstream of add-topic —
pretest, node encoding, the stash → engram-assessor → receipt blind-grading
loop (already topic-agnostic), capstone, commitment, /review,
/coach — is engram's existing machinery, run exactly as documented in
engram/skills/*/SKILL.md.
Step 0 · Environment
Same as every other entry point into the forked engram (see this
directory's README.md § Invocation):
export ENGRAM_ROOT="<abs path>/AgentOS/longform-practice/engram"
export ENGRAM_HOME="<abs path>/AgentOS/longform-practice/state"
Step 1 · Gate check
node "$ENGRAM_ROOT/../scripts/session_context.js" "<note-path, relative to ObsVault/>"
(Or resolve directly: AgentOS/longform-practice/scripts/session_context.js.)
Reads state/eligibility.json, runs the maturity gate against AnkiConnect,
and matches the note's domain/sub_domain frontmatter against
state/corpus_exemplars.json — all in one call, returning:
{
"note": "100_concepts/Separable Equations.md",
"ready": true,
"problem_types": [{ "type": "...", "cases": ["...", "..."] }],
"exemplars": { "problem_families": [...] },
"exemplars_status": "found"
}
If ready is false, stop and tell the user why — don't proceed to Step 2:
reason |
Meaning |
|---|---|
not-eligibility-confirmed |
The note hasn't been through vault-maintenance Step 3's propose/review exercise yet (or was, but not confirmed). Run vault-maintenance first. |
maturity-gate-not-cleared |
Confirmed eligible, but not every flashcard tied to this concept has cleared the 21-day/no-recent-lapse gate yet (result.maturity has the per-card detail). Keep reviewing in Anki. |
anki-unreachable |
AnkiConnect didn't respond — open Anki with the plugin running and retry. problem_types/exemplars are still returned in this case so the eligibility/exemplar picture is visible even without a maturity verdict. |
exemplars_status is informational, never blocking: found (this
sub_domain has been distilled), not-yet-distilled (mapped but not yet
piloted — proceed without exemplar grounding), or unmapped (no vault
sub_domain correspondence yet — same).
Step 2 · Short intake
Same shape as engram/skills/learn/SKILL.md step 1, minus the open "why"
question — the goal is already fixed by problem_types. Ask only:
- Prior exposure (arrow-key): never touched it / seen it, shaky / comfortable with neighbors.
- Check
modelinterests (python3 "$ENGRAM" model); if empty, ask for 2–3 things they love, same as/learn.
Then Read the source note (ObsVault/<note-path>) in full — it's the
architect's primary grounding, not a websearch topic.
Step 3 · Spawn the architect with a constrained package
Spawn engram-curriculum-architect (unmodified — same agent file, same tool list, same output schema) with:
topic: the note's title/slug.goal: state plainly that the terminal capabilities are fixed to exactly theproblem_types(and theircases, each as its own node requiring the parent problem-type's prerequisite chain) returned by Step 1 — do not add or drop any. This replaces the architect's own step 1 ("identify the 2–4 terminal capabilities the goal requires") with an already-confirmed answer; steps 2–7 of its method (backward-chain prerequisites, classify arbitrary/threshold, size nodes, personalize, output the standard schema) run exactly as documented.- Source material: the note content read in Step 2, and — only if
exemplars_status == "found"— the matchedproblem_familiesas few-shot grounding for problem variety (structural patterns, not verbatim corpus text; seestate/corpus_exemplars.json's own_comment). - Prior exposure, interests, from Step 2.
Save its output the same way /learn does:
python3 "$ENGRAM" add-topic --file <tmpfile.json>
Step 4 · Hand off to /learn, unmodified
From here, run engram/skills/learn/SKILL.md steps 2–7 exactly as written —
pretest the frontier, encode nodes via the dialogue grammar, verify through
the blind engram-assessor, capstone, book the return, close. This skill's
job ends at add-topic; everything that makes session generation and
grading real is engram's own machinery, untouched.
/review and /coach need no changes at all — engram/skills/review/SKILL.md
operates purely over due/rate against whatever topics exist in state,
with no awareness of how a topic was created, so reviews for a
longform-practice topic behave identically to any other.
Known limitations
See README.md's "Known limitations" section in this directory — rubric
generation, exemplar coverage, and the ready: true end state all carry
the same caveats here as described there.
04 同仓库更多 Skills
vocab-anki
暂无简介
vault-maintenance
暂无简介
transcript-distillation
暂无简介
daily-log
暂无简介
capture-promotion
暂无简介
review
Clear due memory reviews with free recall — the two-minute habit that makes learning permanent. Use when reviews are due, or the user wants to review, practice, or "do my engram reviews".