CtrlK
BlogDocsLog inGet started
Tessl Logo

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

71

Quality

88%

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

88%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 tightly written, highly actionable install workflow with strong validation checkpoints and clear sequencing. The main room for improvement is splitting long bash blocks into bundled reference scripts and trimming a few guardrail sentences.

Suggestions

Move the two long preflight/build bash blocks into bundled scripts under scripts/ and reference them, reducing SKILL.md token load.

Provide a short table of contents or numbered phase summary at the top so the five-phase flow is legible at a glance before the detailed commands.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no explanations of docker, pnpm, or what a PDF is) and every block is functional, but it is long with several bash blocks; a few prose guardrails could be tightened without losing meaning.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands throughout (the npm registry gate curl script, exact cp commands, the exact JSON manifest object, docker run invocations, and vitest/build commands) covering the common cases.

5 / 5

Workflow Clarity

A clearly sequenced Preflight -> Install -> Validate and build -> Restart -> Smoke test flow with explicit validation checkpoints ('Stop on any failure', the 72-hour release gate, image-pin conflict checks) and feedback loops for the destructive rebuild operations.

5 / 5

Progressive Disclosure

Well-organized into clearly labeled sections with one-level-deep references (CONTRIBUTING.md, docs/skill-guidelines.md, docs/SECURITY.md, bundled install files) that are clearly signaled; no bundle reference docs are provided in references/scripts/assets to split content further, so most detail stays inline.

4 / 5

Total

18

/

20

Passed

Description

87%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 specific, complete description that clearly states both capability and trigger conditions with a distinct niche. Minor gains possible by adding file extensions and synonyms to the trigger list.

Suggestions

Add file extensions (e.g. .docx, .pptx, .xlsx, .odt, .rtf, .epub) alongside the application names to broaden natural trigger coverage.

Use third-person voice ('Adds local...') rather than the imperative 'Add' to align with the recommended description style.

DimensionReasoningScore

Specificity

Names a concrete action ('Add local office-document-to-Markdown conversion'), a specific mechanism ('pinned Firecrawl AnyDoc CLI'), and a concrete target ('NanoClaw agent containers') with a full file-type list, though it is essentially one action rather than multiple distinct ones.

4 / 5

Completeness

Explicitly answers both what ('Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI') and when ('Use when agents need to read attached Word, PowerPoint, Excel... without uploading them to a hosted parser').

5 / 5

Trigger Term Quality

Natural application names are well covered ('Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF'), but file extensions and common synonyms (e.g. .docx, .pptx, spreadsheets) are missing.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply scoped to NanoClaw agent containers and local AnyDoc conversion without a hosted parser, with distinct triggers that are unlikely to collide with other skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
nanocoai/nanoclaw
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.