compound
Skill3 starsChanged 3 months agoMITView on GitHub
Document a solved problem as a searchable solution note in the host's Obsidian vault. Captures a single fix with YAML frontmatter for QMD-based agent discovery; delegates the file write to the obsidian-notes skill.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- chrislacey89/skillstheir own version, first seen Nov 4, 2026
- dsonders/claude-skillstheir own version, first seen Oct 20, 2026
- rcelebrone/DotAgentstheir own version, first seen Oct 14, 2026
- Andamio-Platform/coachtheir own version, first seen Oct 13, 2026
- OHOKAYYEAH/claude-skillstheir own version, first seen Oct 13, 2026
- Artifacts7/newsletter-context-kittheir own version, first seen Oct 13, 2026
Used with
Projects with it also use brainstorm, ship and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
nicolasestremSkillbrainstorm
Structured idea generation and solution exploration with systematic analysis.
Also in 3 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- m-xlsea/ruoyi-plus-soybean★ 328same name
- garagon/nanostack★ 206same name
- team-attention/hoyeon★ 173same name
- ai-native-camp/camp-2★ 19same name
- rcelebrone/DotAgents★ 15same name
- Andamio-Platform/coach★ 6same name
- chrislacey89/skills★ 4same name
- toverux/cantrips★ 3same name
- Artifacts7/newsletter-context-kit★ 2same name
- dirkkok101/skills★ 2same name
7 more not listed
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 repository41 other files it gives its agents.
- cadence-goalsSkill
- ci-feedback-loopSkill
- decision-rights-doctrineSkill
- diataxisSkill
- dispatch-gateSkill
- drift-checkSkill
- family-checkSkill
- fix-then-re-review-ladderSkill
- github-projectsSkill
- gitSkill
- goal-treeSkill
- handoffSkill
- improvement-loopSkill
- kb-captureSkill
- kb-compileSkill
- kb-coreSkill
- kb-lessons-bridgeSkill
- kb-lintSkill
- l1-supervisorSkill
- l2-supervisorSkill
- lessons-learnedSkill
- lN-lifecycle-doctrineSkill
- lN-review-doctrineSkill
- medical-recordsSkill
- operator-interview-doctrineSkill
- operator-interviewSkill
- operator-reviewSkill
- planning-workflowSkill
- pr-review-fanoutSkill
- pull-taskSkill
- ralph-wiggumSkill
- reviewSkill
- root-cause-depthSkill
- scan-documentSkill
- self-improvementSkill
- self-verifySkill
- skillifySkill
- task-workflowSkill
- testing-without-mocksSkill
- vault-cloudSkill
- verify-inherited-premiseSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 37
When this skill is invoked:
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Compound Skill
Captures a solved problem as a type=reference note in the host's Obsidian vault, using the vault's real frontmatter convention. Notes are discovered by future agents via QMD hybrid search (BM25 + vector + reranker) over the vault.
Core Concepts
Single-problem focus: Unlike /claude-skills:lessons-learned (session retrospective), /claude-skills:compound documents one solved problem at a time. Lightweight, focused, fast.
Vault-resident: Notes live in the Obsidian vault, not in any repository's docs/. The actual file write is delegated to the obsidian-notes skill (CLI-first); vault location is resolved per-host from ~/.claude/hosts/<hostname>.md.
Schema: Solution notes use the vault's real note convention — there is no dedicated Solution template or problem_type frontmatter field in the vault. Notes are written as type=reference (the closest existing note type). Problem classification (build-error, severity, etc.) is captured as tags, not invented frontmatter keys. See Integration Points below for the property list and operations/document-solution.md for the full field mapping.
Invocation
/claude-skills:compound # Interactive — asks what you solved
/claude-skills:compound timeout in auth flow # Pre-seeded with problem contextExecution
When this skill is invoked:
Step 1: Load operation details
Read(file_path: "${CLAUDE_PLUGIN_ROOT}/skills/compound/operations/document-solution.md")Step 2: Execute the operation interactively
Step 3: Report the created note path in the vault
Operations
Document Solution (Default)
File: operations/document-solution.md
When: User invokes /claude-skills:compound to capture a solved problem.
Quick summary: Gather problem context, generate frontmatter, write a type=reference note via the obsidian-notes skill using the vault's real properties (area/project/status/date/tags/keywords, set explicitly via property:set — no template).
Output
Creates a solution note at:
<vault>/Notes/<YYYY>/<MM>/<YYYY-MM-DD>-<slug>.md<vault> is resolved by the obsidian-notes skill from the host config.
Integration Points
- Vault Reference template:
<vault>/Templates/Reference.md— the note type compound builds on; frontmatter schema is the vault's standardtype/area/project/status/date/tags(plus the real, registeredkeywordsfield). Body sections (Problem, Symptoms, Root Cause, Solution, Prevention) are caller-composed, not template-defined. - Obsidian-notes skill:
~/.claude/skills/obsidian-notes/SKILL.md— CLI surface (create,property:set,append) used for the write, plus the non-blocking failure contract. - Host config:
~/.claude/hosts/<hostname>.md## Obsidiansection — vault path, CLI binary. - Retrieval: QMD hybrid search over the vault —
skills/task-workflow/references/solution-search.mddefines the canonical query protocol used byinit-workspace,planning-workflow, and other read-side callers. - Lessons-learned bridge: Phase 3d of
/claude-skills:lessons-learnedmay invoke/claude-skills:compoundfor problems with concrete, reusable fixes.
See Also
/claude-skills:lessons-learned— Session retrospective; bridges to/claude-skills:compoundfor concrete fixes./claude-skills:self-improvement— Apply recommendations to skills.obsidian-notesskill — CLI surface for vault writes.
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.

