CtrlK
BlogDocsLog inGet started
Tessl Logo

recap

Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.

69

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, well-structured instruction skill with concrete tool calls, an exact output template, and an explicit anti-pattern guard against fabrication. The main gap is schematic rather than literal query construction in the recall step and validation living in a checklist rather than inline in the workflow.

Suggestions

Replace the schematic "<top concepts>" recall query with a concrete derivation rule (e.g., "query = top 3 words from the session title/first prompt") so the guidance is copy-paste ready.

Fold the key checklist items into the workflow as explicit inline checkpoints (e.g., a "verify totals match shown counts before emitting" step) to embed validation in the flow.

Confirm the referenced ../_shared/TROUBLESHOOTING.md exists or point to a resolvable path so the single external reference does not dangle.

DimensionReasoningScore

Conciseness

Every section earns its place with no padding — the tool calls, expected-output template, terse Why/Anti-patterns/Checklist blocks, and step list assume Claude's competence and add only what it would not already know.

5 / 5

Actionability

Provides concrete tool calls with parameters (memory_sessions {"limit": 30}, memory_recall with limit) and an exact output template, but the per-session recall query is left as a schematic placeholder ("<top concepts>") rather than a fully specified value.

4 / 5

Workflow Clarity

A clearly numbered five-step sequence (parse args → call tool → filter → group → list → totals) with a separate Checklist and WRONG/RIGHT anti-pattern guard; validation is present but lives outside the flow rather than as in-line validate→fix→retry checkpoints.

4 / 5

Progressive Disclosure

This short (~56-line) single-purpose skill is well-organized with clear section headers and only one one-level-deep reference (the optional shared troubleshooting pointer), meeting the simple-skill exception for top progressive-disclosure marks.

5 / 5

Total

18

/

20

Passed

Description

83%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 concrete, well-scoped, and pairs a clear capability statement with explicit natural-language triggers. It is a strong, near-complete description with only minor room for synonym/variation coverage and distinctiveness polish.

Suggestions

Add one or two more natural trigger variations (e.g., "catch me up", "summary of this week's work") to push trigger-term coverage toward comprehensive.

Tighten distinctiveness by noting the boundary against sibling skills inline (e.g., "for a rollup, not a single-session deep-dive") to further reduce overlap with handoff/session-history.

DimensionReasoningScore

Specificity

Names the domain (agent sessions) and several concrete actions — "Summarize", "grouped by date", "highlight observations per session", "rollup of recent work" — with only minor coverage gaps, so it sits above the 1-2 action anchor but below comprehensive multi-action coverage.

4 / 5

Completeness

Explicitly answers both "what" (summarize sessions grouped by date with per-session highlights) and "when" via a concrete "Use when the user asks..." trigger clause, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural verbatim phrases users would say ("recap", "what have we been doing", "today", "this week", "rollup of recent work") with good synonym coverage, though a few natural variations are missing so it falls just short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The "current project" scoping and distinctive triggers ("recap", "what have we been doing") give it a clear niche, with only minor overlap risk against closely related session skills noted in See also.

4 / 5

Total

17

/

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.

Validation15 / 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
rohitg00/agentmemory
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.