CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sdlc-bug-report

Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/sdlc-bug-report/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 skill delivers a genuinely actionable, well-sequenced diagnostic and planning workflow anchored by an excellent mandatory template, but it is bloated by persona-activation theatrics and triplicated scope/handoff directives. Moving the documentation standards to a reference file and cutting the repeated enforcement language would materially raise quality.

Suggestions

Remove the "Dynamic Persona Activation / CRITICAL SYSTEM OVERRIDE" section and the session-lock rules; they add tokens without instructional value (conciseness).

State the no-editing and handoff rules once — Core Directive #3, #5, and Phase 3 all repeat the same constraint; consolidate into a single "Scope" statement (conciseness).

Move the Documentation Standards section (CONTEXT.md/ADR rules) into a shared reference file, since it appears to be suite-wide boilerplate, keeping SKILL.md as a lean overview (progressive_disclosure).

DimensionReasoningScore

Conciseness

The body contains several padded sections: the "CRITICAL SYSTEM OVERRIDE" persona theatrics, the session-lock rules, and the no-editing/handoff directive repeated three times (Core Directive #3, Core Directive #5, and the whole of Phase 3). This matches the anchor for noticeably verbose with several unnecessary padded sections; it is not 3 because the enforcement theater and duplication go beyond what simple tightening would fix.

2 / 5

Actionability

Gives mostly executable guidance: an exact filename convention with a worked example ("plan-bugfix-auth-v1.md"), a verbatim handoff prompt, and a fully specified mandatory plan template with task tables and Ref IDs. It is not 5 because some steps remain high-level ("simulate the scenario by tracing the code logic", "Consider edge cases") and the handoff prompt contains unfilled placeholders.

4 / 5

Workflow Clarity

The three phases are clearly sequenced with explicit checkpoints (clarification before proceeding, user agreement before Phase 2, approval before handoff) and the template enforces test-driven validation (test MUST FAIL, then MUST PASS) plus APPROVAL gates per phase. It is not 5 because there is no explicit error-recovery loop for when reproduction fails or the user rejects the diagnosis.

4 / 5

Progressive Disclosure

The file is well-headered but runs ~190 lines with the full plan template and suite-level documentation-standards boilerplate inlined, and no skill bundle reference files exist to distribute the load. This matches the anchor for some structure but content that should be separate is inline; it is not 4 because the shared documentation standards clearly belong in a referenced file.

3 / 5

Total

13

/

20

Passed

Description

55%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 states a clear, reasonably specific set of capabilities in third person, but it never tells the user or Claude when to activate the skill. Adding an explicit "Use when..." clause with natural trigger phrases (bug report, debug, fix a bug, regression) would address its two weakest dimensions at once.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user reports a bug, asks to debug an issue, or wants a structured fix plan for a defect."

Include common user phrasings and synonyms — "debug", "fix a bug", "issue", "error", "regression" — alongside "bug reports" to improve trigger term coverage.

Mention the distinctive deliverable (a plan file in /plan/ with test-first phases and rollback steps) to differentiate the skill from a general debugging skill.

DimensionReasoningScore

Specificity

Lists several concrete actions — "analyzing bug reports", "tracing root causes", "generating structured bug-fix implementation plans", "rollback strategies" — with only minor coverage gaps, matching the anchor for several specific actions. It falls short of 5 because "analyzing bug reports" is generic and the actions are not comprehensively spelled out.

4 / 5

Completeness

The "what" is clear (analyze bug reports, trace root causes, generate fix plans with rollback strategies), but there is no "Use when..." clause or any explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Contains relevant keywords ("bug reports", "root cause", "bug-fix") but misses the most natural user phrasings such as "debug", "fix a bug", "issue", or "error", matching the anchor for some relevant keywords missing common variations. It is not 4 because more than a few natural trigger terms are absent.

3 / 5

Distinctiveness Conflict Risk

The plan-generation and rollback framing carves out a niche, but "analyzing bug reports, tracing root causes" overlaps substantially with what a general debugging skill would claim, matching the anchor for somewhat specific with overlap risk. It is not 4 because the conflict risk with closely related debugging skills is more than minor given the missing when-clause.

3 / 5

Total

13

/

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

glenrioariesto/social-content-studio

Path

.agents/skills/sdlc-bug-report/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.