CtrlK
BlogDocsLog inGet started
Tessl Logo

documenso-incident-runbook

Manage incident response for Documenso integration issues. Use when diagnosing production incidents, handling outages, or responding to Documenso service disruptions. Trigger with phrases like "documenso incident", "documenso outage", "documenso down", "documenso troubleshooting".

64

Quality

77%

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 ./plugins/saas-packs/documenso-pack/skills/documenso-incident-runbook/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and code, and reasonably well-sequenced, but it suffers from an orphaned, unlinked reference file whose content is duplicated inline and from inconsistent validation feedback loops across its scenarios. Tightening duplication and signaling the implementation guide would materially improve it.

Suggestions

Link references/implementation-guide.md from the body (e.g., a '## Detailed procedures' section pointing to it) and remove the inline-duplicated severity table, diagnostic commands, and circuit-breaker class so SKILL.md stays a concise overview one level deep.

Add explicit validate→fix→retry loops to Scenario 2 (database issues) and Scenario 3 (webhooks), e.g. after a fix run 'docker exec documenso curl -s http://localhost:3000/api/health' / re-send a test webhook and only close once confirmed.

Move the large circuit-breaker TypeScript block and the communication/post-incident templates into the implementation guide, keeping only a short pointer plus the single most-used snippet in SKILL.md.

DimensionReasoningScore

Conciseness

The ~216-line body is mostly concrete operational content (severity table, scenarios, circuit-breaker class, checklists) rather than concepts Claude already knows, but it duplicates material that also lives in references/implementation-guide.md (severity levels, diagnostic commands, procedures, circuit breaker), matching the score-2 anchor 'Mostly efficient but includes some unnecessary explanation or could be tightened'. Not score 3 because the inline duplication of bundle content wastes tokens; not score 1 because it does not pad with basic explanatory concepts.

2 / 3

Actionability

Quotes executable commands such as 'curl -s https://status.documenso.com/api/v2/status.json', 'docker exec documenso-db pg_isready -U documenso', 'openssl pkcs12 -in /path/to/signing-cert.p12 ...', and a complete TypeScript DocumensoCircuitBreaker class — copy-paste ready, matching the score-3 anchor 'Fully executable code/commands; specific examples; copy-paste ready'. Not score 2 because the examples are real and complete rather than pseudocode.

3 / 3

Workflow Clarity

Scenarios are numbered and sequenced (Scenario 1 has explicit if/then branching, Scenario 4 ends with 'Verify: create and sign a test document', and there are post-incident and webhook checklists), but validate→fix→retry feedback loops are inconsistent — Scenario 2 runs diagnostics with no fix/verify loop and Scenario 3 is a flat checklist — matching the score-2 anchor 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'. Not score 3 because explicit validation checkpoints are not present across all procedures; not score 1 because sequences and some checkpoints/checklists do exist.

2 / 3

Progressive Disclosure

A bundle file references/implementation-guide.md exists but is never linked or signaled from the body, while overlapping content (severity levels, diagnostics, procedures, circuit breaker) is duplicated inline; the body's only pointer is to a sibling skill ('see documenso-data-handling'), matching the score-2 anchor 'references present but not clearly signaled; content that should be separate is inline'. Not score 3 because the reference is not well-signaled and content is not appropriately split with navigation; not score 1 because sections are organized and there is no deep reference nesting.

2 / 3

Total

9

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 strong: it explicitly states what the skill does and when to use it, with natural, distinctive Documenso-specific trigger phrases in third person. Its only weak spot is specificity, where the action verbs are high-level synonyms rather than a list of distinct concrete operations.

Suggestions

Replace the synonymous verbs (manage/diagnose/handle/respond) with distinct concrete actions the skill performs, e.g. 'diagnose API errors, run diagnostic probes, enable circuit-breaker degradation, rotate API keys, and recover self-hosted containers'.

Optionally surface the highest-value trigger ('documenso down') earlier in the description so the most natural user phrase leads the 'when' clause.

DimensionReasoningScore

Specificity

Quotes 'Manage incident response for Documenso integration issues' and 'diagnosing production incidents, handling outages, or responding to Documenso service disruptions' — it names the domain and several action verbs, but they are synonymous high-level verbs (manage/diagnose/handle/respond) rather than multiple distinct concrete operations, matching the score-2 anchor 'Names domain and some actions, but not comprehensive'. Not score 3 because it lacks a list of distinct concrete actions like the 'extract text, fill forms, merge documents' example; not score 1 because it does name the domain and specific actions beyond a bare 'helps with'.

2 / 3

Completeness

Quotes 'Manage incident response for Documenso integration issues' (what) and an explicit 'Use when diagnosing production incidents, handling outages, or responding to Documenso service disruptions. Trigger with phrases like...' (when), matching the score-3 anchor 'Clearly answers both what AND when with explicit triggers'. Not score 2 because the 'Use when...' clause is explicitly present rather than implied.

3 / 3

Trigger Term Quality

Quotes explicit triggers 'documenso incident', 'documenso outage', 'documenso down', 'documenso troubleshooting' — these are natural phrases a user would actually say, including the colloquial 'documenso down', matching the score-3 anchor 'Good coverage of natural terms users would say'. Not score 2 because it covers several common variations rather than just one keyword.

3 / 3

Distinctiveness Conflict Risk

Quotes 'Documenso integration issues', 'Documenso service disruptions' and Documenso-prefixed triggers — a clear niche tied to a specific SaaS product with distinct triggers, matching the score-3 anchor 'Clear niche with distinct triggers; unlikely to conflict'. Not score 2 because the Documenso qualifier makes overlap with other skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.