weekly-recap

Generate a repo-local weekly delivery recap from GitHub, Slack, calendar, and docs evidence by default, using best-effort collection for unavailable non-GitHub sources. Produces recap, status update, and brag-candidate files. Use when the user asks for a weekly summary, weekly report, status report, standup notes, progress update, accomplishments list, what they did this week, or what they accomplished.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

This is a well-crafted, highly actionable skill with a clear multi-step workflow, concrete CLI commands, and strong guardrails including prompt-injection defenses. Its main weakness is length: the three full output templates and repeated security warnings inflate the token cost. Progressive disclosure would benefit from splitting output shapes and config examples into separate bundle files.

Suggestions

Move the three output shape templates (recap.md, status-update.md, brag-candidates.md) into separate bundle files and reference them from the main SKILL.md to reduce token cost.

Consolidate the security/guardrail guidance—the untrusted-data warning appears both in step 5 and the Guardrails section; merge into one location.

Dimension	Reasoning	Score
Conciseness	The skill is fairly long (~200+ lines) and includes substantial detail that is valuable but could be tightened. The config file examples, full output templates, and example requests add bulk. Some sections like the detailed `gh` commands are necessary, but the three full output shape templates could be referenced externally. The guardrails section partially repeats the inline injection warning from step 5.	2 / 3
Actionability	The skill provides fully executable `gh` CLI commands with exact flags and JSON fields, concrete YAML config examples, precise output file templates, and a clear 9-step workflow. Claude can follow this without guessing at any step.	3 / 3
Workflow Clarity	The 9-step workflow is clearly sequenced with explicit validation checkpoints: step 2 verifies tool availability with a stop condition, step 5 cross-references and marks unverifiable claims, step 6 has explicit qualification criteria for brag candidates, and step 9 specifies what to report. The error handling (warn and skip unavailable tools, stop only if no tool works) provides clear feedback loops.	3 / 3
Progressive Disclosure	The skill references external config files (`tools.yaml`, `projects.yaml`, `rubric.md`) appropriately, but all three output templates are inlined in full, making the file quite long. These templates could be split into separate reference files. No bundle files are provided to offload this content, and there are no references to external documentation for advanced features.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly communicates what the skill does, what sources it uses, what it produces, and when it should be triggered. It uses third person voice, lists concrete actions and outputs, and provides comprehensive trigger terms that match natural user language. The description is thorough without being unnecessarily verbose.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: generating a weekly delivery recap, collecting from GitHub/Slack/calendar/docs, producing recap/status update/brag-candidate files. Very concrete about inputs and outputs.	3 / 3
Completeness	Clearly answers both 'what' (generate repo-local weekly delivery recap from multiple sources, produce recap/status/brag files) and 'when' (explicit 'Use when...' clause with comprehensive trigger phrases).	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'weekly summary', 'weekly report', 'status report', 'standup notes', 'progress update', 'accomplishments list', 'what they did this week', 'what they accomplished'. These are highly natural phrases.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche: weekly delivery recaps from specific sources (GitHub, Slack, calendar, docs) producing specific output files. Unlikely to conflict with other skills due to the very specific combination of inputs, outputs, and use case.	3 / 3
	Total	12 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: javiermolinar/dope-brag
Commit: 2d9f95a

Reviewed: 22 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.