deploy-agent

Deploy Bindu agents to various environments with safety checks and verification

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/deploy-agent/SKILL.md

Quality

Content

77%

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 and workflow-clear with strong validation for a risky deployment operation, but it is monolithic and somewhat redundant across its Safety/Guardrails/Execution-Contract sections. Splitting detailed material into reference files and de-duplicating the guardrail rules would improve token efficiency and structure.

Suggestions

De-duplicate the rules repeated across Safety, Execution Contract, and Guardrails into a single source of truth to reduce token cost.

Move the rollback procedure, deployment-record JSON, and output-format templates into a reference file (e.g. references/rollback.md) with a one-level-deep pointer from SKILL.md to improve progressive disclosure.

Replace the hardcoded timestamp/version in the deployment-record example with placeholders to avoid implying time-sensitive values.

Dimension	Reasoning	Score
Conciseness	Per-step bash is lean and avoids explaining concepts Claude knows, but the Safety, Execution Contract, and Guardrails sections repeat the same rules (e.g. "Never deploy without passing tests" appears three times) and the illustrative output/record templates pad the body, so it could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash throughout (uv run pytest, alembic upgrade head, docker build/run, curl health-retry loops) with real flags and concrete environment handling, matching the level-3 executable anchor.	3 / 3
Workflow Clarity	A clear 7-step sequence carries explicit validation checkpoints (tests/pre-commit must pass, env-var checks, migration before/after, health retry loop with MAX_RETRIES and failure exit) plus a rollback feedback loop, satisfying the level-3 anchor for a destructive deployment operation.	3 / 3
Progressive Disclosure	Sections are well-organized with no nested references, but no bundle files exist and the ~340-line body is monolithic — rollback, output-format, and env-config content that could be split into reference files is all inline, matching the level-2 "content that should be separate is inline" anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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, distinctive niche and concrete deploy action but lacks any explicit "when to use" trigger guidance and uses vague phrasing ("various environments"). It is solid but incomplete for discoverability.

Suggestions

Add an explicit "Use when..." clause naming the natural trigger terms (e.g., deploying Bindu agents to staging/production, rollback needs, deployment verification).

Replace "various environments" with the concrete environments (local, staging, production) to improve specificity and trigger-term quality.

List the key actions in the description (e.g., run tests, apply migrations, verify health, support rollback) instead of the generic "safety checks and verification".

Dimension	Reasoning	Score
Specificity	It names a domain and some actions ("Deploy Bindu agents", "safety checks and verification") but "various environments" is vague and the actions are not enumerated, matching the level-2 anchor rather than the multi-action level-3 example.	2 / 3
Completeness	The what (deploy Bindu agents with safety checks) is stated, but there is no "Use when..." clause or equivalent trigger guidance for when Claude should invoke it, capping completeness at 2 per the missing-trigger guideline.	2 / 3
Trigger Term Quality	"Deploy" is a natural keyword a user would say, but common variations like staging/production/rollback are absent and "various environments" is generic, so it has some relevant keywords while missing common ones.	2 / 3
Distinctiveness Conflict Risk	"Deploy Bindu agents to various environments" names a specific, identifiable niche (Bindu agent deployment) that is clearly distinguishable from other skills and unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: GetBindu/Bindu
Path: .agents/skills/deploy-agent/SKILL.md
Commit: 7b1ff75

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.