Core
- When to use it
- The cross-role toolkit every pack builds on: structured intake, document critique, the review council, output hygiene, and the decision graph behind a codebase, plus the ship-a-draft wrapper. Installed automatically with every role pack.
- Covers
- Get a draft ready to ship (3), Design the system (1), Build and review software (1)
- Where you decide
- G5 review — ship-a-draft → critique
- Size
- 5 skills · 1 loop · 1 gate, 1 needs a person
20–45 minutes a session
npx skilldrop-cli install --pack core
Installs 5 skills.
Other ways to install
The pack's loops too, each as an invokable skill:
npx skilldrop-cli install --loop --pack core
In Claude Code, as a plugin (after /plugin marketplace add sananthanarayan/skilldrop):
/plugin install core@skilldrop
Into Cursor, Kiro or another IDE:
npx skilldrop-cli install --pack core --ide cursor
Start here: Turn rough notes into a structured brief, then get a verdict on the draft
Paste this into your agent:
Here are my notes from today's planning call: <paste them>. Turn them into a brief, then critique the draft you write from it.
- How to tell it worked
- brief-intake returns a structured brief with gaps tagged, and doc-critique ends with a verdict: SHIP IT, SHIP WITH CHANGES, MAJOR REWRITE or WRONG ARTIFACT.
- If nothing happens
- If neither skill activates, check that
brief-intake/SKILL.mdanddoc-critique/SKILL.mdexist in your skills folder (~/.claude/skills/by default). In Claude Code, start a new session after installing.
A typical session
When: You have rough notes, a transcript or a ticket and want a finished document, not a first draft. About 20–45 minutes.
You bring:
- the raw material: notes, a Slack thread, a transcript or a ticket
- the kind of document you want at the end, such as an ADR, a runbook or an exec summary
- answers to the gaps the brief flags as missing
-
- You
- Paste the raw material and name the document you want it to become.
- You get
- A structured brief with every field tagged explicit, implied, inferred or missing, plus a list of what the next step will refuse to start without.
- You decide
- Answer or explicitly accept each missing field before drafting; the brief never fills them in for you.
-
- You
- Hand over the draft you wrote from the brief, by hand or with any generator skill.
- You get
- A critique that opens with a verdict and lists findings as blocker, major, minor or nit, each pointing to the section and suggesting a fix.
- You decide
- Gate G5: SHIP IT or SHIP WITH CHANGES moves on; MAJOR REWRITE sends you back to the brief; WRONG ARTIFACT means you need a different kind of document.
-
- You
- Run it on the settled draft and say where it is going (markdown, commit message, plain text).
- You get
- The draft with invisible Unicode, provenance trailers and chat closers stripped, prose tells quoted with rewrites, and a 'Not touched' list.
You end with: A reviewed, cleaned document with its verdict, the changes it carried, and a note of what the scrub did not touch.
Loops
- ship-a-draft — Take raw mess to a stakeholder-ready artifact by wrapping any skilldrop generator in the two passes either side of it — structured intake before, critique and machine-residue scrub after.
intake → draft → critique [G5] → polish
Compare Core with another pack
Skills in this pack (5)
- brief-intake Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, slide-outliner) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need. standard
- context-graph Map the decisions behind a codebase from its ADRs, RFCs and design records — each record's status and date, what supersedes or amends what, which records cite which, the files and folders each decision governs, and with git the commits that implemented it and the commits that changed each decision's code since it was made, and who made them — then answer "why is it like this?" from the record and check the record is still true. Finds supersessions only one side records, current decisions pointing at code that is gone, code that has drifted from its decision, two current decisions governing the same path, and references to records that don't exist. Use when the user asks "why do we use X", "which decisions govern this file or service", "is this ADR still current", "has the code drifted since we decided this", "are our ADRs out of date", "what was decided before I change this", wants a map of the architecture decisions, or is onboarding onto a codebase's history. standard
- council-review Convene a council of distinct senior-engineer personas (Architect, Security, Operator/SRE, Pragmatist, User-Advocate, plus optional bench seats) to deliberate a decision, design, or code change — each takes an independent stance, the genuine disagreements are surfaced as named cruxes, and a Chair issues a reconciled verdict that records dissents and states what would change the decision. The "Claude Council." Use when a choice has real tradeoffs and one reviewer's voice isn't enough: architecture decisions, risky changes before merge, RFC/design scrutiny, "should we adopt X?", rewrite-vs-refactor, or a pre-mortem. heavy
- doc-critique Review an existing document — ADR, design doc, runbook, exec summary, tech-comparison matrix, deck outline, decision log — and produce a structured critique against the same quality bars the skilldrop generators enforce. Categorizes findings by severity (blocker / major / minor / nit), points to the exact section/line, and suggests a concrete fix for each. Use when the user wants a second-pair-of-eyes review before sharing a doc, or has been handed someone else's artifact and wants to know what to push back on. heavy
- output-hygiene Review agent-written text before it ships and strip the machine artifacts it carries — invisible Unicode, non-breaking spaces, homoglyphs, harness-added provenance trailers, trailing chat closers — then flag the prose tells a script cannot catch, each quoted with a rewrite. Use when the user wants to clean up AI-generated output, asks to remove a Claude watermark, attribution footer, or "Generated with" line, wants a draft that does not read as machine-written, or needs a pre-ship hygiene pass on a document, commit message, or pasted chat answer. standard