CtrlK
BlogDocsLog inGet started
Tessl Logo

session-search

For CLI agents WITHOUT subagent support (e.g., Codex CLI). Search previous code agent sessions for specific work, decisions, or code patterns.

57

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/aichat/skills/session-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The skill body is highly actionable with concrete commands and a clear worked example, and is well-organized as a self-contained file, but it carries some padded install content and lacks explicit validation/feedback checkpoints in its workflow.

Suggestions

Trim the Error Handling section: keep the install hint but drop the full curl-based uv/rustup installers, or move them to a reference file.

Add an explicit feedback checkpoint in the workflow, e.g. 'If search returns nothing, retry with broader terms before reporting no results' as a named step rather than only a constraint.

Make the jq parsing step concrete with a sample command (e.g. `jq -r '.[] | {session_id, snippet}'`) so step 3 is executable rather than described.

DimensionReasoningScore

Conciseness

The body is mostly efficient with tight workflow and example sections, but the Error Handling block carries full install/prerequisite payloads (Node.js 18+, Rust/Cargo, curl installers for uv and rustup) that are tangential to the core search task and could be trimmed.

2 / 3

Actionability

It provides copy-paste-ready executable commands (`aichat search --json -n 10 "[query]"`, `-g "project"`), concrete jq parsing targets, exact file paths (`~/.claude/projects/*/[session-id].jsonl`), and a worked example with realistic output.

3 / 3

Workflow Clarity

The five numbered steps are clearly sequenced and guarded by explicit constraints (max 3 files, ALWAYS --json, never infer), but there are no validate-then-fix feedback checkpoints; the guardrails are constraints rather than an explicit retry/recovery loop, leaving checkpoints implicit.

2 / 3

Progressive Disclosure

No bundle files exist and none are needed; the content is organized into well-signaled single-level sections (Workflow, Output Format, Example, Constraints, Error Handling), which is appropriate progressive disclosure for a self-contained skill.

3 / 3

Total

10

/

12

Passed

Description

57%

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 states a clear, distinctive purpose with a well-scoped audience, but lacks an explicit 'Use when' trigger and relies on a single action verb, which limits specificity and completeness to the middle band.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a CLI agent needs to recall past sessions, decisions, or code patterns it discussed earlier.'

Broaden trigger-term coverage with natural phrasings like 'session history', 'past work', or 'what did we previously decide'.

Add a second concrete action (e.g. 'Search and summarize previous code agent sessions') to lift specificity from one verb to multiple distinct actions.

DimensionReasoningScore

Specificity

It names the domain ('previous code agent sessions') and several search targets ('specific work, decisions, or code patterns'), but only commits to a single concrete action verb ('Search') rather than multiple distinct actions like the level-3 anchor requires.

2 / 3

Completeness

The 'what' is clearly stated ('Search previous code agent sessions...'), but there is no explicit 'Use when...' trigger; the 'For CLI agents WITHOUT subagent support' clause is an audience qualifier, not a when-to-use trigger, so per the guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Phrases like 'code agent sessions', 'work, decisions, or code patterns' are relevant natural terms, but common variations a user might say ('session history', 'find past work', 'what did we discuss') are absent, so coverage is partial rather than complete.

2 / 3

Distinctiveness Conflict Risk

The 'For CLI agents WITHOUT subagent support (e.g., Codex CLI)' qualifier carves out a clear, narrow niche that makes it unlikely to trigger for the wrong skill.

3 / 3

Total

9

/

12

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
pchalasani/claude-code-tools
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.