CtrlK
BlogDocsLog inGet started
Tessl Logo

brag-summarize

Curate and append source-backed Wins from repo-local weekly evidence to an existing Markdown Wins ledger while deduplicating prior entries. Use for brag-doc updates, accomplishments lists, wins tracker updates, and monthly, quarterly, or custom-period curation. For promotion cases, self-reviews, summaries, or other audience-specific prose, use evidence-prose after the Wins are curated.

80

1.33x
Quality

91%

Does it follow best practices?

Impact

100%

1.33x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No findings from the security scan

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.

A well-structured, actionable instruction-only skill with a clear sequenced workflow, concrete templates and path patterns, and strong guardrails. The main gaps are minor: a little tightening room on conciseness and the absence of an explicit post-append verification checkpoint.

Suggestions

Add an explicit post-append verification step (e.g., re-read the target and confirm the new period heading and Wins are present and existing text is byte-for-byte unchanged) to close the workflow validation gap and support a workflow_clarity of 5.

Tighten the opening paragraph and the "Ledger only" contract bullet, which restates the intro, to reduce minor redundancy and push conciseness toward the lean anchor.

If any detail grows (e.g., legacy STAR/Source-data parsing rules or extended strong-signal examples), move it to a one-level-deep reference file so progressive_disclosure can reach the clear-overview anchor.

DimensionReasoningScore

Conciseness

Lean and efficient with no concept explanations Claude already knows; every section earns its place. Minor trimming possible (the opening sentence "The ledger preserves facts that later writing cannot reconstruct" and slight restatement of "Ledger only" vs the intro), keeping it just below the lean-everything-earns-its-place anchor.

4 / 5

Actionability

Concrete and copy-paste-ready for an instruction-only skill: exact path patterns ("<root>/weekly/YYYY-Www/{brag-candidates.md,recap.md}"), a fill-in Win shape template, explicit verb choices ("handled", "responded to", "resolved"), and an unambiguous 7-step workflow. Absence of executable code is not penalized because the guidance is fully actionable.

5 / 5

Workflow Clarity

A clearly sequenced 7-step workflow with real checkpoints — stop-and-ask on ambiguous insertion, dedup reporting, and a final report of appended/skipped/missing/partial counts. Validation is present (not absent) so it is not capped at 3, but there is no explicit post-append verification step, leaving a minor gap below the explicit-feedback-loop anchor.

4 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and the skill references no external files, so there is no nesting or buried-reference problem. The body is well-sectioned (Contract, Defaults, Win shape, Workflow, Guardrails, Example requests) with easy navigation; scored 4 rather than 5 because, at over 50 lines with no offloaded detail, the simple-skill full-score exception does not strictly apply even though organization is good.

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.

A strong, third-person description that concisely states both the concrete capability and the triggering use cases, with explicit hand-off guidance to a sibling skill for adjacent tasks. It avoids fluff and over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Curate and append source-backed Wins from repo-local weekly evidence", "deduplicating prior entries" — covering curation, appending, source-backing, and deduplication with comprehensive coverage of the domain.

5 / 5

Completeness

Explicitly answers both: what ("Curate and append source-backed Wins ... to an existing Markdown Wins ledger while deduplicating prior entries") and when ("Use for brag-doc updates, accomplishments lists, wins tracker updates, and monthly, quarterly, or custom-period curation").

5 / 5

Trigger Term Quality

Surfaces the natural phrases users actually say — "brag-doc updates", "accomplishments lists", "wins tracker updates", plus period qualifiers (monthly/quarterly/custom) — with multiple synonyms for the same intent.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (repo-local weekly evidence → append-only Markdown Wins ledger) and adds explicit boundary guidance ("For promotion cases, self-reviews, summaries ... use evidence-prose after the Wins are curated"), minimizing wrong-skill triggers.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
javiermolinar/dope-brag
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.