brief-from-pile
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.
npx skills add mohitagw15856/pm-claude-skills --skill brief-from-pile --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Brief From Pile Skill "Here's the folder — get up to speed and tell me what matters" is a real task with a bad default: reading everything start-to-finish, drowning evenly, and producing a summary of *documents* instead of an answer to *questions*. The pile discipline inverts it: define the brief's questions first (what does the reader need to decide or understand?), map the pile cheaply (what each doc is, its date, its likely contribution — the [repo-map](../repo-map/SKILL.md) philosophy applied to documents), read *against the questions* (deep where they're answered, skim where they're not), reconcile the disagreements between documents (piles always disagree — dates usually explain it), and keep the provenance trail, because a brief that can't say "per the Q3 postmortem" gets re-derived by the first skeptic. ## What This Skill Produces - **The pile map** — every document: what it is, date, author-context, and its likely contribution to the questions - **The extraction** — findings organized by the brief's questions (never by source document), each with its citation - **The reconciliation** — where documents conflict: the resolution (usually recency or authority) or the honest
- What This Skill Produces
- Required Inputs
- Framework: The Pile Rules
- Output Format
- The Pile Map
- The Brief (by question)
- The Honesty Ledger
- Quality Checks
- Anti-Patterns
What does the brief-from-pile skill do?
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.
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill brief-from-pile --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.