CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fixing-continuum-issues

Group Continuum issues by root cause, discuss fix tradeoffs before editing, implement one tested pull request per group, test the combined train, suggest merge order, and record shadow merge predictions.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/aws-continuum/skills/fixing-continuum-issues/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 an exceptionally concrete, well-sequenced workflow with strong validation checkpoints and real, clearly-signaled reference files. Its weaknesses are verbosity from repeated policy restatements and inline content (PR template, patch-delivery rules) that would be better split into reference files.

Suggestions

State the merge/publication prohibitions once in an early "Non-negotiables" section and reference it elsewhere instead of restating them in sections 3, 5, 7, and the publication-mode text.

Move the PR description template (the 8-section order, Mermaid rules, and viewport/screenshot rules) into a reference file under references/ and link to it from section 5.

Consider moving the patch-delivery-mode policy (source type / patchCreationPolicy branching) into its own reference file, keeping only the decision summary in the body.

DimensionReasoningScore

Conciseness

The body is dense and imperative with no teaching of concepts Claude already knows, but it is noticeably repetitious and could be tightened: the merge prohibition recurs across at least five places (e.g. "the developer merges every PR" in sections 3, 7, and the publication-mode text), publication-mode rules span two sections, and several long policy sentences restate constraints already established. This fits "mostly efficient but includes some unnecessary explanation or could be tightened" better than the minor-trim level of 4.

3 / 5

Actionability

Concrete, mostly executable guidance throughout: exact commands ("git worktree add", "git show-ref --verify refs/heads/<branch>", "gh pr create --draft", "timeout 580 bash -c 'until <completion-check>; do sleep 30; done'"), exact paths and limits (".continuum/pr-drafts/", "256 KiB"), an 8-section PR template, and a four-cap on repair loops. Minor gaps remain — placeholder-only constructs and inherently repo-dependent steps like "run the repository's full CI-equivalent suite once" — so it sits just below fully copy-paste-ready.

4 / 5

Workflow Clarity

Eight numbered sections form a clear sequence (report freeze → discussion → isolation → prove with tests → PR criteria → combined train → merge order → post-merge verification) with explicit validation checkpoints and feedback loops: regression tests must "fail on the vulnerable base for the expected reason" and pass on the candidate, group branches are checked "against every criterion" before drafting, branches verified with "git show-ref --verify", worktree cleanliness checked before removal, and error-recovery paths defined (conflicts return to the developer, dirty worktrees are blockers, repair loops capped). This matches the top anchor with checklists and error-recovery loops for a complex process.

5 / 5

Progressive Disclosure

The single bundle reference is clearly signaled one level deep — "Read [local-plan.md](references/local-plan.md)" — and genuinely defers detail (the plans.json schema and consent protocol live there, verified against the actual file). Section headers organize the body well, but ~120 dense lines inline material that could partly live in references (the PR description template, the patch-delivery policy), which keeps it at good-structure-with-minor-gaps rather than the ideal split.

4 / 5

Total

16

/

20

Passed

Description

75%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 highly specific and distinctive, enumerating the full workflow in concrete imperative actions. Its main weakness is the complete absence of "when to use" trigger guidance, which caps completeness and slightly limits natural discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the developer asks to fix, group, or prepare pull requests for Continuum security issues from a completed security report."

Include one or two natural user phrasings as triggers ("fix these findings", "prepare PRs for the security report") so the skill surfaces for common request variations.

DimensionReasoningScore

Specificity

The description lists six concrete, distinct actions — "Group Continuum issues by root cause", "discuss fix tradeoffs before editing", "implement one tested pull request per group", "test the combined train", "suggest merge order", "record shadow merge predictions" — giving comprehensive coverage of the workflow. This matches the multiple-specific-concrete-actions anchor rather than the minor-gaps level below.

5 / 5

Completeness

The "what" is explicit and multi-action, but there is no "Use when…" clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is fully concrete rather than vague, and not 4 because "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural terms users of this niche would say are present ("Continuum issues", "fix", "pull request", "merge order"), but common variations such as "security findings", "vulnerabilities", or "prepare PRs" are absent. Good coverage with a few natural terms missing places it between the 3 and 5 anchors.

4 / 5

Distinctiveness Conflict Risk

"Continuum" names a specific tool with unique artifacts (shadow merge predictions, combined train testing), creating a clear niche with distinct triggers and minimal conflict risk with any other skill. It clearly matches the top anchor.

5 / 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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

aws/agent-toolkit-for-aws

Path

plugins/aws-continuum/skills/fixing-continuum-issues/SKILL.md

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.