CommunityCoding & Developmentgithub.com

josie2479-maker/claude-skills

Test a ready-made list of deliverables, documents or artifacts before anyone commits to tracking it. Use when someone is handed a list from a template, vendor, consultant, PMO framework or AI (\"standard project documents\", \"required artifacts\", \"deliverables checklist\") and asks whether to adopt it, what is really required, what to drop, or what is missing. Tags each item by who requires it (funder, law or regulation with citation, a named person, or standard practice that nobody requires), reads the funder's or agency's own template section by section to find required items the list leaves out, and returns a table plus a drop / keep / add list. Not for building a list from scratch with no list in hand, and not for checking whether finished documents are good.

What is claude-skills?

claude-skills is a Claude Code agent skill that test a ready-made list of deliverables, documents or artifacts before anyone commits to tracking it. Use when someone is handed a list from a template, vendor, consultant, PMO framework or AI (\"standard project documents\", \"required artifacts\", \"deliverables checklist\") and asks whether to adopt it, what is really required, what to drop, or what is missing. Tags each item by who requires it (funder, law or regulation with citation, a named person, or standard practice that nobody requires), reads the funder's or agency's own template section by section to find required items the list leaves out, and returns a table plus a drop / keep / add list. Not for building a list from scratch with no list in hand, and not for checking whether finished documents are good.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/josie2479-maker/claude-skills/tree/HEAD/skills/deliverable-requirement-check

Installed? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Deliverable Requirement Check

License: Released under CC BY 4.0 — free to use, adapt, and share with attribution.

A supplied list of deliverables is a claim about obligation, not proof of it. A list that hangs together, uses the right terms and names only real artifacts can still miss every item the funder actually mandates, and pad the rest with work nobody requires. Its plausibility is what makes it risky, because the person receiving it is about to commit to producing every row.

The question this skill asks of each item is not "is this a real thing?" but "who requires this, and can I cite them?" Where the answer is "nobody", saying so is a finding, not a gap to fill.

When to use

  • Someone has a list in hand (from a template, vendor, consultant, framework or AI) and is deciding whether to adopt or track it.
  • The work is funded, regulated or overseen by a body that publishes its own requirements, templates or checklists.

Not for: drafting a list from nothing (start from the funder's template instead), or reviewing the quality of finished documents.

Method

1. Catalogue the supplied list as given

Number every item exactly as supplied. Don't merge, rename or add yet. Record where the list came from and its date, if known.

2. Get the governing sources, and read them

Identify who funds, regulates or approves the work. Obtain their actual template, checklist or guidance and read its section list. Don't reason from what such a template "probably" contains. Requirements change on effective dates that downstream summaries don't carry, so the source document is the only reliable check. Note each source's title, version and date.

If a governing source can't be reached, say so and mark every conclusion that depends on it as provisional at the point it's made.

3. Tag every item with one authority value

TagMeaningEvidence needed
FunderThe funding or oversight body requires itTemplate section, guidance clause or award condition
Law/RegA statute or regulation requires itCitation to the section
Named personA specific person asked for it, on a dateWho and when
Standard practiceCommon and maybe useful, but no requiring authority was foundWhat was searched

"Standard practice" is a legitimate result, not a failure. Also flag any item that depends on a body or role the project doesn't have (for example a release-signing committee on a project that has none).

4. Find gaps in a separate second pass

Only after step 3, walk the governing template section by section and list each required item the supplied list leaves out. Keep added rows visibly separate from supplied rows, so anyone can tell which came from the source and which the analysis introduced. Cap the additions to what the sources require, and record anything considered and rejected, with a reason. Every added row is work handed to a person.

5. Output

  1. Table: item · source (supplied / added) · authority tag · citation or evidence · notes (depends on a missing body, overlaps another item, etc.).
  2. Drop / Keep / Add:
    • Drop: standard-practice items with no requiring authority that the team doesn't need. Say why each one goes.
    • Keep: items with a cited authority, plus any standard-practice items the team chooses to keep, labelled as a choice.
    • Add: required items missing from the list, each with its citation.
  3. Sources read: title, version and date of each governing document, and any that couldn't be reached.

Example (generic)

An open-source library receiving a software grant is handed a 17-item "standard release documents" list from a consultant, grouped into design, build, launch and maintenance. Reading the grant's own milestone template shows 5 required deliverables. Two of them are on the list under different names; three aren't on it at all. Of the 17 supplied items, 2 match the grant, 1 is required by the license-compliance terms of a dependency, 2 were asked for by the lead maintainer, and 12 are standard practice with no requiring authority. Three of those 12 assume a security review team the project doesn't have. Result: keep 5, add 3, drop or make optional 12.

Without the check, the team would have committed to 17 items and missed 3 that the grant reviewers actually check.

Before reporting done

  • Every supplied item has exactly one authority tag.
  • Every Funder or Law/Reg tag has a citation from a source actually read.
  • The governing template was read section by section, or its absence is stated and conclusions are marked provisional.
  • Added rows are visibly separate from supplied rows.
  • Drop / Keep / Add is present and each line has a reason.

Individual skills in this repo

This repo contains 3 individual skills — each has its own dedicated page.

josie2479-maker/claude-skills

Verify factual claims before delivering them. Use before any answer or deliverable the user will act on, forward, or share with others — rules, policy, legal, financial, date, or product facts — and whenever they say 'is that right', 'double-check that', 'verify this', 'fact-check', 'are you sure', or 'source?'. Exception: vetting a claim someone else handed the user is critical-thinking-walkthrough; fetching page text is reliable-fetch (this skill calls it).

josie2479-maker/claude-skills

Interview the user about something they are ABOUT TO BUILD, before any of it is built — a feature, a system, an automation, a workflow, a document structure. Use when a plan exists only in their head or as a rough idea and the design decisions are still open: \"grill me\", \"interview me about this\", \"help me think this through before I build it\", \"what am I not deciding\", \"ask me what you need to know\". Works the design as a dependency tree, asking one answerable question per round (the one that unblocks the most decisions first) with a recommended answer attached, and never asking anything it could look up itself. BOUNDARY — this is front-loaded, for decisions not yet made. Reviewing a plan that already exists and stress-testing it for holes is the plc skill. Interrogating information someone else handed you is critical-thinking-walkthrough. If the thing is already written down and the question is \"is this any good\", it is not this skill.

josie2479-maker/claude-skills

Strip AI-essay voice from a document that will be shared outside this conversation — a memo, spec, brief, proposal, SOW, report, or any deliverable going to a supervisor, agency, client, or contractor. Use when asked to \"clean this up\", \"make this professional\", \"take the Claude out of it\", \"de-AI this\", \"make it ready to send\", or when a draft is about to be handed off and has not had a register pass. Also run it unprompted as the last step when drafting any external-facing document. Not for chat replies, personal notes, or internal scratch files — conversational voice is fine there and flattening it is a loss. Not for fiction or other creative writing, where the voice is the point; see the fiction note in the body.

Related Skills