skills/WriteDocs/SKILL.md
Author project documentation that future humans (and AI sessions) actually read. Covers TLDRs for tools, READMEs, runbooks, journals. USE WHEN write documentation, create tldr, tool one-pager, document a cli, write readme, runbook, journal entry, capture knowledge about a tool, distill a session into reusable notes.
npx skillsauth add n4m3z/forge-core WriteDocsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Documentation is a contract with the reader. The reader is usually a future-you or a future AI session that has lost the surrounding context. Good docs collapse what would otherwise be a fresh round of trial and error into a single read. Bad docs are noise — they bloat the repo, drift from reality, and train readers to skip docs entirely.
This skill collects the shapes that have proven worth the maintenance cost. Pick the matching companion for the doc you're about to write; if none fits, the work probably belongs in code comments, a commit message, or an ADR rather than a new doc file.
| Type | Trigger | Companion | | -------- | ------------------------------------------------------------------------------------ | ------------------- | | TLDR | "write tldr", "tool one-pager", "document a cli", "distill a tool from this session" | @Tldr.md |
Other types (README, runbook, journal, migration guide) live in adjacent rules or are queued for future companions; add a row here when a new companion is authored.
| Thought | Reality |
| -------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| "I'll document every flag and option" | Comprehensive ≠ useful. The reader needs the 80% path, not the man page. |
| "Better to over-document than under-document" | Wrong volume kills docs. Over-detail trains readers to skip; under-detail makes them grep. |
| "I'll add a ## Future Work section" | Future-work sections rot. Track in a backlog file, not in the doc. |
| "This needs a top-level overview section" | If the first paragraph isn't already the overview, the doc is misstructured. |
| "Let me link to upstream docs and call it done" | Docs that only link out fail when upstream restructures. Capture the load-bearing bits. |
| "I'll keep this in sync with the code" | Anything inline that mirrors the code drifts. Reference by path/line; restate sparingly. |
development
Reactive correction and root-cause fix. USE WHEN something went wrong, user is frustrated, demands a correction, says wtf, what the hell, why did you, that's wrong, this is broken, no not that, stop. Executes the immediate fix, then hunts the upstream artifact that caused it and creates a corrective change.
development
Decompose a research question into sub-queries, spawn parallel WebResearcher agents per angle, synthesize findings with citations and explicit confidence. USE WHEN the user asks to research, investigate, look online, look up, dig into, find sources, gather evidence, or survey what's known about a topic. Single-pass; for multi-round adversarial research use ResearchCouncil in forge-council.
development
Review your own staged changes via a code-review TUI before triggering a commit. USE WHEN about to commit, walking through your own staged diff, self-reviewing before approval, tuicr, revdiff, git diff cached.
tools
Apply targeted transforms to prompt-shaped documents: align conventions, debrand vendor references, minimize filler, rescope tool grants, extract bulk reference, adapt for downstream repos. USE WHEN refining an adopted skill, polishing an authored skill/rule/agent, removing rot, or porting prompts across repos.