Files
DottaandPaperclip 953b315dfb Shorten skill frontmatter descriptions (#9353)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Paperclip agents can load repository and catalog skills, and Codex
renders skill names and frontmatter descriptions into startup context.
> - Long descriptions consume the fixed skill metadata budget before
Codex can use the progressively disclosed skill bodies.
> - The repo `.agents/skills` descriptions and a few shipped catalog
descriptions had grown into operational documentation instead of short
trigger metadata.
> - This pull request keeps the strongest trigger language in
frontmatter while leaving detailed procedures in each skill body.
> - The benefit is lower prompt overhead, more reliable skill
triggering, and a regression guard that prevents description drift from
returning.

## Linked Issues or Issue Description

No public GitHub issue found for this maintenance item.

### Pre-submission checklist

- [x] I have searched existing open and closed issues and this is not a
duplicate.
- [x] I am working against `master`.
- [x] I have confirmed the issue originates in Paperclip's shipped skill
metadata, not in a local agent adapter or provider.

### What happened?

Codex startup renders discovered skill names and frontmatter
descriptions into a fixed skill metadata budget. Several repository
skill descriptions and one shipped catalog description had grown into
long-form operational guidance, which can force Codex to truncate
descriptions before the model has enough trigger signal to select the
right skill.

### Expected behavior

Skill frontmatter descriptions should stay short trigger summaries: one
capability sentence plus a “use when” clause. Detailed procedures should
stay in the skill body and load only after the skill triggers.

### Steps to reproduce

1. Inspect `.agents/skills/*/SKILL.md` and
`packages/skills-catalog/catalog/**/SKILL.md` frontmatter descriptions.
2. Measure folded YAML `description` values.
3. Observe descriptions above the intended short-trigger range,
including descriptions above 300 characters.
4. Run the new shipped catalog test to verify future descriptions stay
capped.

### Paperclip version or commit

Reproduced on `master` at `cc81eefb6047d8eaf57faf785f421c03dc97073c`.

### Deployment mode

Local dev / source checkout metadata inspection. This is not
database-related.

### Installation method

Built from source.

### Agent adapter(s) involved

Codex, because Codex startup uses the skill metadata prompt budget. The
metadata source itself is core repository/catalog content.

### Database mode

Not database-related.

### Access context

Not applicable; this is static repository metadata.

### Node.js version

`v22.22.2` in the verification environment.

### Operating system

Linux container environment.

### Relevant logs or output

Final measurement after this PR: 29 source `SKILL.md` files, max
description length 215 chars, 5,449 total description chars, estimated
1,363 description tokens at 4 chars/token.

### Relevant config

None.

### Additional context

The shipped catalog manifest was regenerated so the generated package
metadata matches the edited catalog `SKILL.md` sources.

### Privacy checklist

- [x] I have reviewed all pasted output for PII and redacted where
necessary.

## What Changed

- Shortened long `.agents/skills/*/SKILL.md` frontmatter descriptions to
concise capability plus use-when trigger clauses.
- Shortened the over-budget shipped skills catalog descriptions for
wireframe, Paperclip capsules, and reflection coach.
- Regenerated `packages/skills-catalog/generated/catalog.json` so
shipped metadata matches source skill frontmatter.
- Added a Vitest regression guard that caps repo skill source
descriptions and generated catalog descriptions at 300 characters.

## Verification

- `pnpm --filter @paperclipai/skills-catalog build:manifest`
- `pnpm --filter @paperclipai/skills-catalog test` — 5 files passed, 19
tests passed
- `pnpm --filter @paperclipai/skills-catalog typecheck`
- Final measurement: 29 source `SKILL.md` files, max description length
215 chars, 5,449 total description chars, estimated 1,363 description
tokens at 4 chars/token.

Note: the clean PR worktree was created from `origin/master` and
contains only this commit, but it does not have `node_modules`; running
`pnpm --filter @paperclipai/skills-catalog test` there failed at
tool/package resolution (`vitest`, `tsc`, `@paperclipai/shared`). The
dependency-equipped workspace passed the commands above before the
commit was cherry-picked onto the clean branch.

## Risks

Low risk. This changes skill metadata and tests only. The main risk is
over-trimming a useful trigger phrase, mitigated by keeping explicit
“use when” clauses and leaving detailed guidance in the skill bodies.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

OpenAI GPT-5 Codex coding agent via Paperclip/Codex, with shell and
file-edit tool use. Exact API model ID and context window were not
exposed in the runtime.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-07-10 08:46:20 -05:00

3.7 KiB
Raw Permalink Blame History

name, description
name description
wiki-ingest Use when an operation issue asks to ingest a captured `raw/` source into the LLM Wiki, or the user says "ingest <slug>". Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles.

Wiki Ingest

Turn one source document into durable, interlinked wiki knowledge.

Inputs

  • An operation issue with operationType: "ingest" assigned to you.
  • A raw/ path mentioned in the issue body (always treat raw/ as immutable).
  • The operation issue's target wikiId, spaceSlug, and space root (otherwise stop and surface the missing config to the requester).

Workflow

  1. Read context first.
    • Read the target space's AGENTS.md for page conventions (filenames, frontmatter, voice, citation style).
    • Read the target space's wiki/index.md to see what already exists.
    • Read the target space's last ~20 entries of wiki/log.md to avoid re-ingesting a source or re-resolving a contradiction someone else already filed.
  2. Read the source end to end with wiki_read_source, passing the operation issue's wikiId and spaceSlug. Do not skim. Note the source's structure, claims, dates, and anything that contradicts existing pages.
  3. Plan, then confirm — but only if the user is in the loop. If the operation came from a routine (no live user), proceed. If a user is asking interactively, summarise the 3–5 takeaways you intend to file and ask which to emphasise before writing.
  4. Write the source page at wiki/sources/<slug>.md — ~300–800 words, frontmatter per the wiki schema, neutral voice, key claims with quoted excerpts where they carry weight. The source page is the canonical citation target for everything else this skill writes.
  5. Update or create downstream pages in entities/, concepts/, and synthesis/. A typical ingest touches 5–15 pages; resist creating pages for ideas that only appear once.
  6. Wire the cross-links. Every claim that comes from the source cites it as (see [[wiki/sources/<slug>]]). Every entity / concept mentioned by name on more than one page links to its dedicated page.
  7. Flag contradictions; do not silently overwrite. When new material disagrees with an existing page, append a > ⚠ contradicted by [[wiki/sources/<slug>]] (YYYY-MM-DD) callout to the older page and note the conflict in the log.
  8. Refresh wiki/index.md with one-line summaries for any new pages.
  9. Append a log entry in wiki/log.md:
    ## [YYYY-MM-DD] ingest | <source title>
    - source: raw/<filename>
    - new pages: [[...]], [[...]]
    - updated pages: [[...]], [[...]]
    - notes: <one-line synthesis or open question>
    

Voice

  • Terse, factual, neutral. Reference material, not narrative.
  • No "Today I learned" or "This is interesting because" framing.
  • Quote the source verbatim when paraphrasing would lose precision.

Verification

Before closing the operation issue:

  • Source page exists at wiki/sources/<slug>.md with valid frontmatter and a sources: field pointing to the raw path.
  • Every new or updated page links back to the source page or a downstream page that does.
  • wiki/index.md lists every new page under the right category with a one-line summary.
  • wiki/log.md has the ingest entry with the exact filename heading format (so grep "^## \[" wiki/log.md keeps working).
  • Any contradiction between the new source and an older page is annotated, not silently overwritten.
  • No file under raw/ was modified.

Tools

wiki_list_sources, wiki_read_source, wiki_search, wiki_read_page, wiki_write_page. Always include the operation issue's wikiId and spaceSlug.