Skip to content
Skills Library
Programming · Writing

documentation-updates

/documentation-updates

Capture durable project or workflow knowledge discovered during work. Use when a mistake, hidden constraint, repeated question, or changed behavior reveals a documentation gap. To root-cause one specific mistake the agent just made and let the user pick fixes, use `learn` (`/learn`) instead.

Repository
ai-config ↗
Licence
GPL-3.0
Last repository change
08.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 08.10.2026, without references to retired models or APIs.

Licence

GPL-3.0, otwarta.

What it does and when to use it

Capture durable project or workflow knowledge discovered during work. Use when a mistake, hidden constraint, repeated question, or changed behavior reveals a documentation gap. To root-cause one specific mistake the agent just made and let the user pick fixes, use `learn` (`/learn`) instead.

Original author description

Capture durable project or workflow knowledge discovered during work. Use when a mistake, hidden constraint, repeated question, or changed behavior reveals a documentation gap. To root-cause one specific mistake the agent just made and let the user pick fixes, use `learn` (`/learn`) instead.

How it works

  1. Research reports
  2. Workflow
  3. Include
  4. Exclude
Original SKILL.md headings · 45 lines, 277 words
SKILL.md preview
---
name: documentation-updates
description: >-
  Capture durable project or workflow knowledge discovered during work.
  Use when a mistake, hidden constraint, repeated question, or changed
  behavior reveals a documentation gap. To root-cause one specific mistake
  the agent just made and let the user pick fixes, use `learn` (`/learn`)
  instead.
---

# Documentation Updates

Record knowledge where future readers will naturally look for it, without
turning instruction files into a transcript or catch-all memory store.

## Research reports

Store durable research, investigation, audit, and comparison reports under
`docs/research/` relative to the current repository root by default. Defer to a
location specified by the user, the repository, or a focused workflow.

## Workflow

1. Identify the durable lesson and who needs it.
2. Find the authoritative home: nearby code or tests, project documentation,
   an applicable agent rule, a focused skill, or the project's task/memory
   system. For agent rules, prefer `AGENTS.md` over `CLAUDE.md`, and the
   shared global rules file (e.g. `~/.agents/AGENTS.md`) over any single
   agent's global file, so all agents stay in parity. Use an agent-specific
   file only for that agent's own features.
3. Update the smallest relevant source. Link to existing detail rather than
   duplicating it.
4. Check for conflicting or stale guidance and update it in the same scope.
5. Validate examples, commands, links, and any generated or mirrored files.
6. Summarize what changed and why.

## Include

- non-obvious constraints and operational gotchas;
- decisions that remain true beyond the current session;
- reliable recovery or verification procedures; and
- changed user-facing behavior that belongs in product documentation.

## Exclude

- ordinary facts visible from the codebase;
- chronological work logs better suited to issues or comments;
- credentials, personal data, or confidential context;
- speculative rules based on a single unexplained failure; and
- global guidance when the lesson is project-specific.

Do not block unrelated work for a documentation review unless the user asked
for an approval checkpoint or the documentation is required for safe use.

Versions

The database has no other skills named documentation-updates.

Database snapshot: 13.11.2026 · package version e9db45001050 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100learn
    Turns an incident or mistake from a session into a durable rule with a mechanism (test, hook, ratchet or check) in the current project, and drafts a protocol issue when the lesson is generic. Use after an incident is fixed, when the user says "this must not happen again",…
  • 100learn
    Use when a non-trivial lesson emerged (a pitfall avoided, a correction, a discovered convention) and you want it recorded as a rule (Why + When to apply) at the top of docs/LEARNINGS.md.
  • 90mistake-to-constraint
    Use when a mistake repeats. Encode it as the strongest guard — type or runtime, lint, test, directory convention, then a rules line — and log it in CONSTRAINTS.md.
  • 100learn
    Update project CLAUDE.md with strategic knowledge discovered during this session — or CLAUDE.local.md when the discovery is per-developer/per-checkout and that file already exists. Defers to any project- or user-defined memory-placement guidance instead of overriding it. Use…
  • 100correct
    Turn a repeated agent mistake into a check that fails, at the highest layer that can hold it (architecture, then types, then lint, then tests, docs last), and prove the check catches the real past mistake. Use when the user corrects the same mistake again, says it keeps…
  • 90learn-from-mistake
    Find why an agent produced a bad result, strengthen the code, repository, verification, tooling, or workflow that enabled it, then retry the original task. Use when the user asks to learn from a mistake, prevent recurrence, or postmortem an agent failure.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.