debrief

Review what agents accomplished, surface loose ends across sessions

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/debrief/SKILL.md

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 tight, well-structured instruction skill: lean prose, executable git commands for inspection, and a clear synthesis checklist. It earns top marks on conciseness and progressive disclosure, with actionability and workflow clarity just one notch below due to the synthesis being guidance rather than fully specified examples.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — a two-sentence overview, terse section intros, and direct commands with no padding or explanation of concepts Claude already knows. Every line earns its place, so it matches the 'lean and efficient' anchor.	5 / 5
Actionability	Provides concrete, copy-paste-ready git commands ('git log --oneline -15 --all --decorate', 'git status --short', 'git stash list') for the inspection steps, while the synthesis section gives actionable bullet guidance. Not a 5 because the synthesis bullets are guidance rather than fully specified examples.	4 / 5
Workflow Clarity	Clear numbered sequence (Recent Commits → Work In Progress → Synthesis) with a structured synthesis checklist (What Landed, Loose Ends, Connections, Next Actions). The skill is read-only so the destructive/batch validation cap does not apply; not a 5 only because there are no explicit error-recovery feedback loops.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with well-organized sections and a clearly signaled 'See Also' cross-reference to related skills; no external bundle references are needed, satisfying the simple-skill exception for a top score.	5 / 5
	Total	18 / 20 Passed

Description

53%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 conveys a clear, distinct purpose and two concrete actions, but lacks an explicit 'Use when…' trigger clause and has only modest keyword coverage, which caps both completeness and trigger-term quality at 3. Adding a concrete trigger phrase and a few synonyms would lift it into the 4 range.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when an agent run finishes, when resuming work across sessions, or when the user asks for a debrief/loose-ends check.'

Broaden trigger terms with natural synonyms: 'debrief', 'post-agent recap', 'loose ends', 'uncommitted work', 'session handoff'.

Tighten the action list with one more concrete verb (e.g. 'consolidate commits, uncommitted work, and TODOs into a debrief') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (agent work review) and two concrete actions ('Review what agents accomplished', 'surface loose ends across sessions'), but coverage is not comprehensive. Not a 4 because the actions are limited and 'surface loose ends' is somewhat abstract rather than enumerating specific artifacts.	3 / 5
Completeness	Has a clear 'what' (review agent work and surface loose ends) but no explicit 'Use when…' clause; the 'when' is only weakly implied. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes some natural terms a user might say ('agents', 'loose ends', 'sessions') but misses common variations or synonyms. Not a 4 because keyword coverage is thin — there are only a handful of phrases and no synonyms.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly specific niche (post-agent debrief across sessions) with distinct triggers and low conflict risk. Not a 5 because 'review what agents accomplished' could still overlap with general code-review skills.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tslateman/duet
Path: skills/debrief/SKILL.md
Commit: 5647baf

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.