docs

Portable helper anchor (single-statement). The bundled-helper commands in this skill resolve the skill directory inline at each call site via ${CLAUDE_SKILL_DIR:-<absolute skill base directory this runner reports in context>}. When $CLAUDE_SKILL_DIR is set and non-empty (Claude Code), run each command exactly as written. Otherwise locate the directory yourself — this text lives in a file inside it, whose sibling ../../scripts/ directory exists — by replacing the placeholder with the skill base directory the runner reports in context (e.g. a Base directory for this skill: line) and accepting a candidate only once ls <candidate>/../../scripts/ succeeds in the same shell the helper commands run in. If a path form is rejected, use the form that shell reports (pwd shows it); a Windows-form base directory (C:\...) may first be converted with one standalone wslpath -u '<path>' then cygpath -u '<path>' command in order — no platform branch — using the output only when the command succeeded and printed a non-empty path, else falling through to the filesystem check. Resolve the anchor inline at every call site — never capture it into a shell variable that a later statement reads, because some runners' inline-bash marshaling drops such variables. If no candidate validates — neither $CLAUDE_SKILL_DIR nor a runner-reported base directory whose ../../scripts/ exists — stop and report that the helper anchor could not be resolved rather than running a command with a broken path.

Consumer prompt extension (load first). Before doing this skill's work, load any consumer-supplied prompt extension for this skill and honor it. From the repo root, emit the granted vendored-literal leading token first:

.prflow/vendor/prflow/scripts/load-prompt-extension.sh docs

On a command not found / No such file / exit-127 reading (this repository's own local tier, where .prflow/vendor/ is materialized only at runtime), re-invoke the same helper with the .prflow/vendor/prflow/ prefix removed (scripts/load-prompt-extension.sh docs) as a single leading-token statement. If that too is not found (a non-Claude-Code runner where neither repo-relative path exists), fall back to the portable anchor form:

"${CLAUDE_SKILL_DIR:-<absolute skill base directory this runner reports in context>}"/../../scripts/load-prompt-extension.sh docs

If the invocation fails because the helper path does not exist (No such file, exit 127, or the platform equivalent) on every form above, that is the anchor-resolution failure described in the Portable helper anchor note above — fix the anchor, don't report a missing extension. If instead the harness refuses the command outright — a permission denial rather than a missing file — the extension's state is unestablished: report that in the run's output and never treat it as a clean policy pass (unknown is not zero). Otherwise, if the helper exits non-zero, a consumer extension exists but could not be loaded — surface its stderr message and do not silently proceed as if none existed. If it exits 0 and prints text, treat that text as additional instructions appended to the end of this skill's own prompt for this run — it is upgrade-safe, consumer-owned customization committed under .prflow/prompt-extensions/. If it exits 0 and prints nothing, proceed unchanged.

Objective

You are an AI Documentation Agent for code repositories. You perform up to three sequential documentation tasks in a single session, sharing context between them so that findings from earlier steps inform later steps. Steps 1 and 2 are individually gated by config flags (see below) — a disabled step is skipped, not failed.

This skill is a router: it composes no prose of its own, delegating each step to a docs-family skill that composes and reads the shared writing standard itself. So it does not read lib/writing-standard.md directly — the standard is read by the skill each step dispatches.