CtrlK
BlogDocsLog inGet started
Tessl Logo

summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

60

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/summarize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body is a strong, execution-ready reference for a simple CLI skill: fully runnable commands, exact flag syntax, and clear trigger phrases, with an explicit escalation workflow for oversized transcripts. Its one real defect is the PilotDeck migration/review note, which is meta-noise unrelated to using the skill and is the main drag on conciseness.

Suggestions

Delete the 'PilotDeck Migration Note' section entirely — the temp source path and review status have no operational value in the shipped skill.

If the skill grows, move the flags and config detail into a reference file linked from a short 'Advanced options' section.

DimensionReasoningScore

Conciseness

The operational content is lean — command blocks, flag syntax, and env var names with zero concept explanations — but the 'PilotDeck Migration Note' section (source temp path, review status, 'metadata was removed or should be ignored during review') is ~5 lines of process noise that earns no token, fitting 'mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

Commands are copy-paste ready and cover the common cases: 'summarize "https://example.com"', the --extract transcript flow, exact flag syntax ('--length short|medium|long|xl|xxl|<chars>'), env var names, and a concrete config.json example. Not below 5 because nothing is pseudocode or missing a runnable detail.

5 / 5

Workflow Clarity

This is a simple single-action skill (run `summarize <input> [flags]`) and that action is unambiguous, with quick-start examples for each input type and an explicit fallback workflow ('If the user asked for a transcript but it's huge, return a tight summary first, then ask which section/time range to expand'). No destructive/batch operations, so no validation cap applies.

5 / 5

Progressive Disclosure

No bundle files exist, and the ~70-line body uses clean, well-labeled sections (When to use, Quick start, YouTube, Model + keys, Useful flags, Config) appropriate to a single CLI skill. It sits just above the 'under 50 lines' bar that would allow a 5 on sections alone, and the PilotDeck note is an organizational blemish, so 'good structure; minor organization gaps' fits best.

4 / 5

Total

17

/

20

Passed

Description

62%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.

The description does a solid job on the 'what' with concrete verbs and an unusually thorough enumeration of input types, but it entirely lacks a 'use when' trigger clause and leans on the highly generic verb 'summarize', creating overlap risk with other summarization tasks. Adding an explicit trigger clause would resolve the completeness cap.

Suggestions

Append a trigger clause such as 'Use when the user asks to summarize or transcribe a link, video, podcast, article, PDF, or local file' to lift completeness from 3 to 5.

Narrow the scope to distinguish it from general summarization (e.g., 'web/video content' rather than any 'local file') to reduce conflict risk with document- or code-summarization skills.

Add one or two file extensions (.mp3, .mp4, .pdf) to strengthen trigger-term coverage.

DimensionReasoningScore

Specificity

Names two concrete actions ("Summarize or transcribe") plus a broad enumeration of input types (URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, local files), matching 'lists several specific actions; minor gaps' — it is more comprehensive than the anchor-3 example but stops at two verbs, short of anchor 5's multiple distinct actions.

4 / 5

Completeness

The 'what' is clearly stated (summarize/transcribe of enumerated media and file types) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3; not lower because the 'what' half is concrete and unambiguous.

3 / 5

Trigger Term Quality

"summarize", "transcribe", "YouTube/videos", "podcasts", "articles", "PDFs" are natural user phrasings with synonym coverage, but common variations and file extensions (.mp3, .mp4, .pdf) are missing, so it fits 'good keyword coverage; a few natural terms missing' rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

"Summarize" is an extremely common request verb and this description could fire for code summaries, document summaries, or conversation digests handled by other skills; the media/URL scope narrows it somewhat but it still fits 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

14

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
OpenBMB/PilotDeck
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.