agentleFS
Slava-codeSlava-code/slava-stack/.claude/skills/add-entry/SKILL.md

add-entry

Skill0 starsChanged 29 days agoMITView on GitHub

File content into the KB: source, comparison, decision, brainstorm, strategy, interview, experiment, advisor or team profile. Use when the user says: save this to the KB, add this, log this, record this, file this for later (with an unread URL: fetch it now). Picks folder and template, fills frontmatter, commits, pushes. Not for todos (add-todo skill) or transcripts (meeting skill).

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Acquire the single-writer lock: Check runs/.lock. If it exists, abort with "another agent is writing, retry later." Otherwise write …

    line 10
  2. Distinctive:

    Classify: Use AGENT-GUIDE.md §"Where does this content go?" to pick the destination folder.

    line 11
  3. Very specific:

    Fill frontmatter: All required fields for the type (see schema/kb-schema.yaml).

    line 13
  4. Distinctive:

    Fill body: Keep required sections per CONVENTIONS §"Required body sections":

    line 14
  5. Very specific:

    Regenerate INDEXes: Run python3 scripts/rebuild-indexes.py.

    line 21
  6. Very specific:

    Stage + commit + push: Use the right commit prefix per CONVENTIONS §"Commit convention".

    line 22
  7. Very specific:

    If the pre-commit lint fails: fix the content (or amend the schema, with a separate schema: commit) — never --no-verify.

    line 25

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/add-entry — Add content to the KB

Steps:

  1. Acquire the single-writer lock. Check runs/.lock. If it exists, abort with "another agent is writing, retry later." Otherwise write <session-id> <ISO-timestamp> to it.
  2. Classify. Use AGENT-GUIDE.md §"Where does this content go?" to pick the destination folder. If ambiguous, ask the user.
  3. Copy template. From schema/templates/<type>.md to the target path. File naming per CONVENTIONS §"File naming" (dated flat file OR entity folder — see comparisons/advisors/discovery/team conventions).
  4. Fill frontmatter. All required fields for the type (see schema/kb-schema.yaml). Do not invent values — ask the user where needed. Always write a description: field (≤120 chars, rule-not-summary, no wikilinks/links, include category keyword — see the template's placeholder hint for examples).
  5. Fill body. Keep required sections per CONVENTIONS §"Required body sections":
    • synthesis: ## Counter-arguments, ## Data gaps
    • decision: ## Why, ## What we're giving up
    • comparison: ## Decision
  6. Stamp any thread this entry resolves. Ask: does this new entry answer an open thread recorded in an existing doc — a ## Open threads bullet, a [?question] / [?decision] tag, an unresolved question you remember from this session? If yes, apply an inline resolution stamp to that doc (CONVENTIONS §"Growth rules" → "Resolution stamps"): **Resolved YYYY-MM-DD → [[this-entry]]:** <one line> at the head of the resolved bullet, original text left below. Add a back-link from this entry's ## Related. Do NOT supersede/rewrite the host doc — it stays live. Stage the stamped doc to commit alongside the new entry. Skip if nothing is resolved (most entries resolve nothing — don't manufacture one). 6a. Check for an existing entry and back-stamp versions. Run python3 scripts/kb-prompt-lookup.py "<entity or slug>" first: if the entity already has a file or hub, update or link it instead of creating a parallel one. If this file replaces an older version (-vN, draft-N, a newer deck), set supersedes: here AND stamp the old file status: superseded + superseded_by: + a > ⚠️ Superseded by [[...]] banner, and update the hub's current-docs row. Lint rejects the commit otherwise. Collateral made for one specific program, customer or project goes in that entity's folder, not strategy/. 6b. Keep current truth current. Ask: does this change what is true now — an outcome, a status, a number, a price, a decision, who someone is? If yes: (a) edit the matching line in STATE.md and bump its as-of: date; (b) update the hub README if the entity has one (see ALIASES.md); (c) add a new row to ALIASES.md for any new recurring name, nickname or transcript mis-spelling; (d) put a one-line outcome banner on older files that still read as open. Stage these in the same commit set. Skip silently if nothing changed.
  7. Regenerate INDEXes. Run python3 scripts/rebuild-indexes.py. It rewrites the destination folder's INDEX.md (and root INDEX.md if a new folder was created). Stage any modified INDEX.md files alongside the new content file.
  8. Stage + commit + push. Use the right commit prefix per CONVENTIONS §"Commit convention". Message format: <prefix>: <verb> <slug>. Always push after.
  9. Release the lock. rm runs/.lock.

If the pre-commit lint fails: fix the content (or amend the schema, with a separate schema: commit) — never --no-verify.

Required reading first time: CONVENTIONS.md, AGENT-GUIDE.md, schema/kb-schema.yaml.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.