Turn a folder of accumulated documents into one decision-ready brief — the skim-map pass over the pile, the extraction against the brief's actual questions, the conflict reconciliation when documents disagree, and the provenance trail back to sources. Use when asked read all this and tell me what matters, synthesize this folder for the new lead, turn these 20 docs into a brief, or what does all this material actually say. Produces the pile map, the question-driven extraction, the reconciled brief with per-claim sources, and the didn't-read honesty ledger.
▸The pile — the documents (or their contents); the map works on what's actually there
▸The reader and their questions — who is this for and what must they decide/understand ("the new lead needs: state of the project, open risks, why past decisions were made") — without questions, the output is a book report
▸The pile's history, if known — why these documents accumulated, which are drafts vs. finals ([doc-versioning-discipline](../doc-versioning-discipline/SKILL.md) status often missing — the map infers and flags)
▸The deadline and depth — an afternoon's brief reads differently than a week's; the map allocates reading time by expected contribution
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓The questions were written before the reading started
✓Reading depth followed the map's contribution estimates
✓Every finding carries its document citation
✓Conflicts were reconciled by stated logic or reported as findings
✓The ledger names the gaps and the skips honestly
⚠️ What it refuses to do
Do not read evenly — the pile's volume distribution is not its importance distribution
Do not organize the brief by document — the reader has questions, not a filing fetish
Do not average conflicting sources — reconcile or report; blend is betrayal
Do not cite nothing — an uncited brief is one skeptic away from being re-done
Do not hide what wasn't read — the ledger converts a limitation into a map for the reader
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp