CtrlK
BlogDocsLog inGet started
Tessl Logo

retrospective-artifacts

Builds and parses structured retrospective artifact folders for troubleshooting, incident review, and delivery retros. Use this skill when capturing session context, synthesizing external context (GitHub, Jira, Mattermost, logs), querying prior retrospectives, or preparing downstream inputs for OKB entries, postmortems, and agent/skills/instruction improvements.

68

Quality

81%

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

85%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 skill body with excellent workflow sequencing, explicit validation gates, and clean progressive disclosure into verified bundle files. The only real improvement area is tightening duplicated guidance (repeated reference paths and focus-directive text) and making script invocations fully copy-paste ready with literal output filenames.

Suggestions

Replace glob-style output placeholders like `github-*.md` with a literal example filename (e.g., `github-issue-1234.md`) so commands are copy-paste ready.

Consolidate the repeated reference path mentions: state each reference once at point of use and drop the redundant restatements in the References and fallback sections.

Merge the 'Manual fallback handoff' section into 'External context acquisition' guidance it points to, since it duplicates one sentence of that reference.

DimensionReasoningScore

Conciseness

The body is efficient and imperative throughout ("Ask 1-3 targeted questions", "Do not proceed to generation until..."), with no explanation of concepts Claude already knows. Minor trimmable redundancy remains: reference paths are repeated in the workflow steps, the References section, and the fallback sections, and the focus-directive guidance overlaps with the checklist reference, so it does not reach anchor 5's 'every token earns its place'.

4 / 5

Actionability

Mostly executable guidance: the script quick reference gives concrete commands (e.g., `python3 scripts/fetch_github_context.py --url "<github-url>" --output "<artifact>/context/github-*.md"`), the folder structure and focus-directive examples are concrete. Minor gaps keep it below anchor 5: output names use glob placeholders like `github-*.md` rather than a literal filename, and no example of a completed invocation is shown.

4 / 5

Workflow Clarity

Both modes are explicitly routed, CREATE mode is a clearly numbered sequence with an explicit gate ("Do not proceed to generation until the required minimum context is present") and a final validation step (frontmatter truthful, referenced paths exist, conservative flag setting), plus error-recovery loops ("If retrieval fails or access is denied, state that clearly and request pasted text") and a checklist reference. This matches anchor 5: clear sequence, explicit validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

The body is a genuine overview that pushes detail into four real, one-level-deep reference files (all verified to exist in references/) and three scripts, each well-signaled at point of use and consolidated in a References section and quick-reference section. Nothing that belongs in a reference file is inlined, matching the anchor-5 example of a clear overview with well-signaled shallow references.

5 / 5

Total

18

/

20

Passed

Description

78%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 well-formed description that clearly separates capability from trigger conditions in third-person voice with strong natural trigger terms. Its main weakness is that the 'what' side compresses two actions (build, parse) into one clause without enumerating the concrete outputs, leaving it slightly less specific than top-scoring examples.

Suggestions

Enumerate the concrete actions on the 'what' side, e.g., 'Builds timestamped retrospective folders with summaries, external context, logs, and code snippets; parses existing retrospectives to answer queries and shortlist learnings.'

Add one or two common user synonyms such as 'retro' or 'post-mortem' to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ("retrospective artifact folders") and two concrete actions ("Builds and parses"), which matches the anchor for 1-2 concrete actions without comprehensive coverage. It does not list several specific actions such as what building or parsing concretely produces, so it sits below anchor 4.

3 / 5

Completeness

It explicitly answers both what ("Builds and parses structured retrospective artifact folders for troubleshooting, incident review, and delivery retros") and when ("Use this skill when capturing session context, synthesizing external context..., querying prior retrospectives, or preparing downstream inputs...") with concrete trigger phrases. It uses the third-person voice for the capability statement, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "troubleshooting", "incident review", "delivery retros", "postmortems", "GitHub, Jira, Mattermost, logs", "querying prior retrospectives". A few natural terms users might say are missing (e.g., "retro", "post-mortem", "writeup"), which fits anchor 4 rather than the comprehensive synonym/extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (structured retrospective artifacts under a dedicated system) with distinct triggers like "okb entries", "postmortems", "querying prior retrospectives". Minor overlap risk with general documentation, note-taking, or postmortem-writing skills, which fits anchor 4 (mostly distinct) rather than anchor 5's minimal conflict risk.

4 / 5

Total

16

/

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
canonical/copilot-collections
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.