courier

Reach Jira and Slack where the Atlassian and Slack MCPs stop, via the `jira` and `slack` CLIs. Use to download a ticket's or thread's attachments, upload a file to a Jira issue or Slack message, delete a Slack post, or write a Jira description with checkboxes or embedded images.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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.

A dense, well-structured, highly actionable skill body with clear workflows and validation. The two gaps are the missing jira-adf.md reference file and the deferral of core operation commands to --help rather than concrete examples.

Suggestions

Add the referenced jira-adf.md file to the bundle (or remove the link) so the one-level-deep reference resolves.

Include one concrete example invocation each for the core operations (download attachment, upload file, delete post) alongside the --help discovery guidance.

Tighten the Slack bot limitations list into a short checklist so the validation cues (invite-and-retry, sandbox rehearsal) are scannable.

Dimension	Reasoning	Score
Conciseness	Lean and information-dense throughout: it skips basic concepts (no "what Jira/Slack is") and packs only non-obvious operational knowledge (bot scopes, exit-0-no-data behavior, mrkdwn vs markdown, ADF), so every token earns its place; it is not level 4 because there are no trimmable over-explanations.	5 / 5
Actionability	Provides copy-paste-ready commands for install, setup, config, and issue-filing, but the core operations the skill exists for (download/upload/delete) are deferred to `--help` discovery rather than shown concretely; this is a justified but real gap, so it is above the incomplete level-3 anchor but below the fully-executable level-5 anchor.	4 / 5
Workflow Clarity	Multi-step sequences (setup hand-off, gap-filing, --help discovery) are clearly numbered with explicit validation checkpoints and feedback loops (unconfigured bin → hand off and stop; HTML-page error → invite bot and retry; confirm hand-off via `config`); the destructive `slack delete` is guarded with sandbox rehearsal and author sign-off, satisfying the destructive-operation validation requirement.	5 / 5
Progressive Disclosure	The body is well-sectioned into clear overview areas and uses a well-signaled, one-level-deep reference ([jira-adf.md](jira-adf.md)) for the ADF detail, but that referenced file does not exist in the bundle, which is a real organization gap that keeps it below the level-5 anchor; it is above level 3 because structure and signaling are otherwise good.	4 / 5
	Total	18 / 20 Passed

Description

83%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.

A strong, specific description that names a clear niche and several concrete actions with low conflict risk. The main gap is trigger-term breadth and slightly less explicit "when" phrasing, which keep it just below a perfect score.

Dimension	Reasoning	Score
Specificity	Lists four concrete, distinct actions ("download a ticket's or thread's attachments, upload a file to a Jira issue or Slack message, delete a Slack post, or write a Jira description with checkboxes or embedded images"), which is comprehensive coverage of the skill's niche; it is not the level below because that anchor only names 1-2 actions.	5 / 5
Completeness	Has a clear "what" (reach MCP gaps via the CLIs with the listed actions) and a "when" via "Reach Jira and Slack where the Atlassian and Slack MCPs stop" plus "Use to...", but the trigger guidance is capability-listed rather than phrased as explicit "when the user wants to..." conditions, so it falls short of the level-5 anchor's concrete trigger phrases while exceeding the weak/implicit-when level-3 anchor.	4 / 5
Trigger Term Quality	Good natural-term coverage ("Jira", "Slack", "attachments", "upload a file", "delete a Slack post", "checkboxes", "embedded images"), but it lacks the synonym/extension breadth (e.g., no "file upload" synonyms or file-type tokens) that marks the level-5 anchor; it clears level 3 because the keywords are natural and relevant, not generic.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche ("where the Atlassian and Slack MCPs stop" — file bytes and take-backs) with distinct triggers and minimal overlap risk; it is not level 4 because the niche is sharper than "minor overlap risk with closely related skills."	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: aabuhijleh/abed-hub
Path: skills/courier/SKILL.md
Commit: 5e27c8c

Reviewed: 1 hour 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.