CtrlK
BlogDocsLog inGet started
Tessl Logo

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting session data.

74

Quality

91%

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

82%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 dense, highly actionable operational reference with concrete SQL patterns, backend-specific guidance, and clear multi-step workflows backed by error-recovery feedback loops. Its main weaknesses are length/monolith structure (no file splitting for the sizable schema and Cost-Tips material) and some repeatable emphatic phrasing that could be tightened.

Suggestions

Split the Database Schema section and the detailed Cost Tips exploration dimensions into reference files (e.g. SCHEMA.md, COST-TIPS.md) referenced one level deep from SKILL.md to reduce the monolith and improve progressive disclosure.

Tighten the Cost Tips section — consolidate the repeated agent_name filter restatements and trim the duplicated 'do NOT' emphatic warnings now stated in multiple workflows.

Add an explicit validation/checkpoint note to the read-only analysis workflows (Tips, Cost Tips, Improve) — e.g. confirm query results are non-empty before drawing conclusions — to bring workflow clarity to the top anchor.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no basic-concept explanations), with non-obvious schema and dialect specifics earning their place; it is not a 5 because the Cost Tips section is expansive and several emphatic 'do NOT' exhortations are repeated and could be trimmed.

4 / 5

Actionability

Fully executable guidance throughout — exact SQL predicates ('WHERE updated_at >= datetime(\'now\', \'-1 day\')'), exact agent_name strings per backend, FTS5 MATCH syntax, quote-escaping rules ('it\'s' → 'it''s'), and concrete output-format templates covering the common cases.

5 / 5

Workflow Clarity

Each workflow is clearly sequenced with numbered steps and includes explicit feedback loops where they matter (query timeout → narrow the window, don't retry; empty results → stop and don't fabricate); read-only analysis workflows lack explicit validation checkpoints, keeping it just below 5.

4 / 5

Progressive Disclosure

Well-organized hierarchical headers (## Workflows, ### per workflow, ## Database Schema, ## Query Guidelines) with in-file cross-references ('re-read the Database Schema section below') providing one-level navigation; not a 5 because it is a ~350-line monolith with no content split into reference files.

4 / 5

Total

17

/

20

Passed

Description

100%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 concise yet comprehensive: it names the domain, enumerates concrete capabilities, and provides an explicit 'Use when...' clause rich with natural trigger phrases and synonyms. It is highly specific, complete, and distinctive with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'standup reports, usage tips, session search, and session reindexing' plus deletion — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ('Analyze Copilot session history for...') and 'when' ('Use when the user asks for...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural user phrases with synonyms are present throughout ('standup' / 'daily summary', 'search or find past sessions by keyword/file/PR', 'reindex their session store', 'deleting session data'), matching how a user would actually ask.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Copilot session store analysis) with distinct triggers (standup, session search, reindex) that are unlikely to fire for unrelated skills.

5 / 5

Total

20

/

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
posit-dev/positron
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.