documenting-decisions
Skill4 starsChanged 3 months agoApache-2.0View on GitHub
Documentation policy — what must be documented and where (ADRs, reviews, discussions, promoted memory), the ADR scope classification (framework/project/hybrid), cross-project propagation, and CLAUDE.md maintenance triggers. Use when creating ADRs or reviews, or deciding where documentation belongs. Cross-refs the selecting-review-gates and syncing-framework-docs skills.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- bostonaholic/rpikittheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- bostonaholic/rpikit★ 19same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adr-writingSkill
- authoring-goal-contractsSkill
- collaborating-asyncSkill
- committing-changesSkill
- cross-agent-dispatchSkill
- feature-status-registrySkill
- grill-meSkill
- grill-yourselfSkill
- handling-micro-fixesSkill
- multi-instance-dispatchSkill
- notifying-the-developerSkill
- orchestrating-goal-loopsSkill
- orchestrating-lean-dispatchSkill
- performance-playbookSkill
- python-project-patternsSkill
- recovering-from-failuresSkill
- running-build-checkpointsSkill
- searching-prior-artSkill
- security-checklistSkill
- selecting-review-gatesSkill
- severity-calibrationSkill
- syncing-framework-docsSkill
- testing-playbookSkill
- wrapping-up-sessionsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 7 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
All architectural decisions → ADR in docs/adr/
- Very specific: line 10
All multi-agent discussions → discussions/ with events.jsonl + transcript.md
- Very specific: line 11
All code reviews → review report in docs/reviews/
- Distinctive: line 12
All public APIs → docstrings in code + module-level docs
- Distinctive: line 13
All agent reflections → reflection files linked to discussions
- Very specific: line 15
All facilitator synthesis events must include a ## Request Context section documenting developer framing (what was requested, scope, …
- Distinctive: line 25
All structured artifacts use YAML frontmatter + Markdown body
- Very specific: line 33
When a framework ADR is accepted, add an entry to ~/.claude/shared-memory/FRAMEWORK_CHANGELOG.md
- Distinctive: line 37
When a rule, command, or agent is created that is framework-universal, note it as a propagation candidate in the commit message
- Distinctive: line 42
Update CLAUDE.md when project conventions change
- Very specific: line 43
Update when new promoted rules are added to .claude/rules/
- Distinctive: line 44
Update when architectural boundaries shift (requires ADR)
- Distinctive: line 45
Every review comment about missing context is a signal that CLAUDE.md needs updating
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Documentation Policy
What Must Be Documented
- All architectural decisions → ADR in
docs/adr/ - All multi-agent discussions →
discussions/with events.jsonl + transcript.md - All code reviews → review report in
docs/reviews/ - All public APIs → docstrings in code + module-level docs
- All agent reflections → reflection files linked to discussions
- Sprint retrospectives →
docs/sprints/ - All facilitator synthesis events must include a
## Request Contextsection documenting developer framing (what was requested, scope, motivation, explicit constraints)
Where
- ADRs:
docs/adr/ADR-NNNN-slug.md - Reviews:
docs/reviews/REV-YYYYMMDD-HHMMSS.md - Discussions:
discussions/YYYY-MM-DD/DISC-YYYYMMDD-HHMMSS-slug/ - Promoted knowledge:
memory/subdirectories - Project conventions:
CLAUDE.md
Format Standard
- All structured artifacts use YAML frontmatter + Markdown body
- ADRs follow the template in
docs/templates/adr-template.md - Review reports follow
docs/templates/review-report-template.md - Reflections follow
docs/templates/reflection-template.md
ADR Scope Classification
- New ADRs must include a
scope:field in frontmatter:framework(universal to all projects),project(this project only), orhybrid(universal principle, project-specific implementation) - Framework-scoped ADRs are candidates for propagation to the template and shared-memory changelog
- When a framework ADR is accepted, add an entry to
~/.claude/shared-memory/FRAMEWORK_CHANGELOG.md - See DISC-20260411-171115 for the propagation architecture decision
Cross-Project Propagation
- When a rule, command, or agent is created that is framework-universal, note it as a propagation candidate in the commit message
- Universal lessons from project-specific incidents belong in
~/.claude/shared-memory/universal-warnings.md, not as propagated rule files - The
/retrocommand includes a cross-project knowledge check (Step 7) that prompts for shared-memory contributions
CLAUDE.md Maintenance
- Update CLAUDE.md when project conventions change
- Update when new promoted rules are added to
.claude/rules/ - Update when architectural boundaries shift (requires ADR)
- Every review comment about missing context is a signal that CLAUDE.md needs updating
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

