CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, lean, and highly actionable skill body with concrete paths, tools, a citation convention, and a verification checklist. The only gap is an explicit error-recovery retry loop within the workflow for batch write operations.

Suggestions

Add an explicit feedback loop in the Workflow for batch write failures (e.g., 'If wiki_write_page fails, surface the error, retry once, then log the failure') to lift workflow clarity to the validation-checkpoint anchor.

Consider a brief mid-workflow validation step (e.g., re-read index.md after writing source page to confirm the slug does not already exist) to catch duplicates before touching downstream pages.

DimensionReasoningScore

Conciseness

Lean and terse throughout — every line is actionable guidance (paths, counts, guardrails like 'treat raw/ as immutable', 'Do not skim') with no explanation of concepts Claude already knows.

5 / 5

Actionability

Provides concrete file paths (wiki/sources/<slug>.md, entities/, concepts/, synthesis/), named tools (wiki_read_source, wiki_write_page), an exact citation format, and a copy-paste-ready log entry template covering the common case.

5 / 5

Workflow Clarity

A clearly sequenced 9-step workflow with a planning checkpoint and a final 6-item Verification checklist, but it lacks an explicit validate-then-fix-and-retry feedback loop mid-process for this batch (5–15 page) operation.

4 / 5

Progressive Disclosure

A short (~50 line) self-contained skill with no bundle files needed, organized into clear sections (Inputs, Workflow, Voice, Verification, Tools), satisfying the simple-skill exception for well-organized structure.

5 / 5

Total

19

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly states both the trigger conditions and the concrete outputs, with third-person imperative voice and no padding. The only minor gap is synonym coverage in the trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles' — covering the full set of page types plus a delegated tool, matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what (create durable source/entity/concept/synthesis/index/log pages) and when ('Use when an operation issue asks to ingest... or the user says "ingest <slug>"') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes the natural verb 'ingest' and the literal phrase users would say ("ingest <slug>") plus 'raw/ source' and 'LLM Wiki', giving good keyword coverage, though a few synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (ingesting captured raw/ sources into the LLM Wiki) with distinct triggers — the operation issue's ingest operationType and the 'ingest <slug>' phrase — giving minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
paperclipai/paperclip
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.