CtrlK
BlogDocsLog inGet started
Tessl Logo

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/public/find-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 content is well-structured and actionable with a clear workflow and a verified helper script reference. Its weaknesses are mild verbosity (definitional padding and full response templates) and a missing post-install validation checkpoint.

Suggestions

Remove the generic definition ('Skills are modular packages that extend agent capabilities...') and condense the two full example response blocks into a compact template to improve token efficiency.

Add an explicit validation step after install (e.g., confirm the skill appears under skills/custom/ and is usable) to close the workflow's validation gap.

Replace the placeholder '/path/to/skill/scripts/install-skill.sh' with the concrete resolved path or a discovery mechanism so the install command is copy-paste ready.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands and examples, but includes unnecessary explanation ('Skills are modular packages that extend agent capabilities with specialized knowledge, workflows, and tools.') and full verbatim response templates that could be trimmed; not a 4 because the padding is more than minor.

3 / 5

Actionability

Provides concrete executable commands (npx skills find, npx skills check, npx skills update, bash scripts/install-skill.sh, npx skills init) with query-to-command examples and a real install script; not a 5 because the placeholder path '/path/to/skill/scripts/install-skill.sh' is not copy-paste ready.

4 / 5

Workflow Clarity

A clear four-step sequence (understand, search, present, install) with a fallback branch for no-results, but it lacks an explicit validation checkpoint confirming the skill installed and loaded correctly; not a 5 due to that minor validation gap.

4 / 5

Progressive Disclosure

Well-organized sections in a single appropriately-sized SKILL.md with a clearly signaled, one-level reference to the real scripts/install-skill.sh; not a 5 because there is little progressive disclosure to evaluate and a couple of inline blocks (the full response templates) could live elsewhere.

4 / 5

Total

15

/

20

Passed

Description

78%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 clearly answers both what the skill does and when to use it, with natural trigger phrases and a distinct niche. Its main weakness is limited action specificity (only discover/install) and a somewhat broad lead-in trigger.

Suggestions

Add one or two more concrete actions (e.g., 'browse, search, install, and update agent skills') to lift specificity beyond the two-action anchor.

Tighten the lead-in trigger so the generic 'how do I do X' is clearly scoped to capability-extension intent, reducing overlap with general assistance skills.

DimensionReasoningScore

Specificity

Names the domain ('agent skills') and two concrete actions ('discover and install') but offers no further actions, matching the anchor for 1-2 concrete actions without comprehensive coverage; not a 4 because coverage is limited to those two verbs.

3 / 5

Completeness

Explicitly states what it does ('Helps users discover and install agent skills') and when to use it ('This skill should be used when the user is looking for functionality that might exist as an installable skill') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases like 'how do I do X', 'find a skill for X', and 'is there a skill that can...', giving good keyword coverage; not a 5 because a few common variants (e.g., 'I need a tool for X') are absent and no file-extension-style synonyms apply.

4 / 5

Distinctiveness Conflict Risk

The agent-skills discovery niche is mostly distinct with clear triggers, but the generic 'how do I do X' phrasing creates minor overlap risk with general assistance skills, keeping it just below a 5.

4 / 5

Total

16

/

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
bytedance/deer-flow
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.