CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

debug-deployment

Debug a failing deployment.

Quality

57%

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 ./tests/workspace/cases/workspaces/agent_workspace/.claude/skills/debug-deployment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

51%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 maximally token-efficient but severely underdeveloped: one underspecified instruction with no location for the referenced run record, no follow-up debugging steps, and no validation checkpoints. The conciseness is admirable, but the skill leaves Claude unable to actually execute the task.

Suggestions

Specify where the run record lives and how to retrieve it, e.g., a concrete path or command, so the single instruction is executable.

Add the subsequent debugging steps (locate the failing step, identify the error, apply a fix) with explicit validation checkpoints so the implied sequence becomes real.

Briefly state what to look for in the run record (error codes, failed stage, timestamps) to make the guidance concrete rather than a bare hint.

DimensionReasoningScore

Conciseness

The body ("Read the run record first.") is a single lean line with zero padding and no explanation of concepts Claude already knows — every token present is doing work, cleanly matching anchor 5 ("Lean and efficient; every token earns its place"). Its underspecification is penalized under actionability and workflow_clarity, not here.

5 / 5

Actionability

"Read the run record first" is a directive but gives no path, command, or location for "the run record" and no follow-up steps, matching anchor 2 ("Minimal concrete guidance; high-level hints but missing the specific steps to execute"). It instructs rather than merely describes, so it stays above anchor 1, and lacks any concrete detail that would reach anchor 3.

2 / 5

Workflow Clarity

The word "first" implies a sequence that is never elaborated — every subsequent step and any validation is absent, matching anchor 2 ("Rough sequence present but many gaps; steps poorly defined; validation absent"). The simple-skill exception cannot apply because the single given step itself is ambiguous (which run record, from where?).

2 / 5

Progressive Disclosure

No bundle files exist, so there are no nested or buried references and no inlined content that belongs in separate files. However, a single headerless line that points to "the run record" without any path or pointer offers no organization or navigation, fitting anchor 3 ("could be better organized; references present but not clearly signaled") more than the well-organized sections required for anchor 5.

3 / 5

Total

12

/

20

Passed

Description

45%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 terse and on-topic, naming the deployment-debugging domain with a few natural trigger words, but it lists no concrete debugging actions and entirely lacks a "Use when" trigger clause, capping completeness. It reads as a minimal stub rather than a complete description.

Suggestions

Add an explicit trigger clause, e.g., "Use when a deployment fails, a rollout is stuck, or a release errors during CI/CD", to answer "when" and raise completeness.

Enumerate the concrete debugging actions and scope, e.g., "Read run records, inspect error logs, check service health, and identify the failing deploy step", to lift specificity.

Include common synonyms users would say (rollout, release, deploy failure) to broaden trigger term coverage.

DimensionReasoningScore

Specificity

"Debug a failing deployment" names the domain but provides only a single generic action with no elaboration, matching the anchor "Names the domain but actions are minimal or generic" (e.g., "Processes PDF files"). It falls below anchor 3, which requires 1-2 concrete actions to be listed.

2 / 5

Completeness

The description states a recognizable "what" (debug failing deployments) but contains no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3. It sits above anchor 2's "vague what" because the action is stated rather than obscured, and below anchor 4 because "when" is entirely absent.

3 / 5

Trigger Term Quality

"debug", "failing", and "deployment" are natural words a user would say, but the description includes no common variations or synonyms (e.g., failed deploy, rollout, release, CI/CD pipeline error). This matches anchor 3 ("Some relevant keywords but missing common variations or synonyms") better than anchor 4's broader coverage.

3 / 5

Distinctiveness Conflict Risk

"Deployment" debugging is somewhat specific as a domain, but the term is broad enough (web deploys, k8s rollouts, CI/CD releases) to overlap with general debugging, CI/CD, and ops skills. This matches anchor 3 ("Somewhat specific but could still overlap with similar skills").

3 / 5

Total

11

/

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

dlt-hub/dlt

Path

tests/workspace/cases/workspaces/agent_workspace/.claude/skills/debug-deployment/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.