CtrlK
BlogDocsLog inGet started
Tessl Logo

session-search

Recover prior Feynman work from session transcripts. Use the optional /search command only when it is installed and visible; otherwise search local session JSONL files directly.

63

Quality

74%

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/session-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 concise, well-organized, mostly actionable skill body with clear sections and a runnable grep example. Its main gaps are a redundant restatement of the fallback conditional and a missing example for parsing JSONL content.

Suggestions

Add a one-line example showing how to extract message.content from a matched JSONL line (e.g., a jq command) to cover the structured-search case.

Remove the redundant restatement of the /search-vs-fallback conditional in the final paragraph since the intro already states it.

Clarify the closing 'structured search' guidance with a concrete next step rather than looping back to /search.

DimensionReasoningScore

Conciseness

Lean and mostly efficient with a concrete grep example and no over-explanation of JSONL, but the opening and closing paragraphs redundantly restate the same '/search when available else direct search' conditional.

4 / 5

Actionability

Provides concrete, copy-paste-ready commands (/search <query>, grep -ril with a real path) and the JSONL schema, but lacks an example for parsing message.content — the common structured-search case.

4 / 5

Workflow Clarity

The two-branch flow (interactive /search if visible, else direct grep) is clear and read-only so no validation cap applies, but there is no error/feedback handling and the closing 'structured search' guidance loops back without a concrete step.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references, and content is cleanly organized into well-signaled sections (Interactive search, Direct file search), meeting the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

70%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 is specific and well-targeted to a distinct niche, but lacks an explicit user-need trigger clause, capping completeness at 3. Trigger terms are good but could include more synonyms.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when the user asks to recover or review prior Feynman sessions') to raise completeness.

Include common synonyms such as 'session history' or 'previous sessions' alongside 'session transcripts' to broaden trigger coverage.

Lead with the primary concrete action (recover prior work) before the conditional fallback detail to strengthen specificity.

DimensionReasoningScore

Specificity

Names the domain ('prior Feynman work from session transcripts') and lists several concrete actions (recover work, use /search, search JSONL directly), with only minor coverage gaps.

4 / 5

Completeness

Has a clear 'what' but the 'when' is only weakly implied — the conditional clause governs /search availability rather than stating an explicit user-trigger 'Use when...' clause, which caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural domain terms ('Feynman work', 'session transcripts', '/search', 'session JSONL files') a user would say, though a few common synonyms like 'history' or 'previous sessions' are missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche tied to the specific Feynman tool ('Feynman work', 'session transcripts', '/search') with distinct triggers and minimal overlap risk.

5 / 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
companion-inc/feynman
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.