CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

mdelapenya/coding-skills

Coding-agent skills for pull-request work and orchestration: an adversarial multi-pass PR reviewer, PR description and title writing, answering review comments, CI failure triage and PR nursing, a DAG orchestrator that delegates to cheaper subagents, and file-channel coordination between agents. Supports GitHub and GitLab.

1.88x
Quality

95%

Does it follow best practices?

Impact

98%

1.88x

Average score across 10 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

generic.mdskills/pr-reviewer/references/agents/

Generic / unknown runtime

Fallback for any agent without a dedicated file here.

Fetch tooling

With a shell, gh and glab are the canonical tools and the skill runs as written. With only a host MCP server, use it for Step 2 metadata (head and base SHA must come from one response) and for linked issues; Step 4's clone still needs a shell. With neither, the user must check out the PR head and paste the metadata; the skill then verifies HEAD == headRefOid and runs the "current branch" path. The skill never manufactures data.

Models

TierRequirementUsed for
Hardthe strongest model available for a sub-taskassessor; escalated reviewer
Mediuma mid-cost modelreviewers A, B, C
Easythe cheapestsummary

With one model only, record it for every pass; the lenses, the assessor's steel-man and the state file still apply.

Fan-out primitive

If the runtime can start isolated sub-tasks with their own prompt (and ideally their own model), each reviewer prompt from references/passes.md is one sub-task, dispatched together, with no reviewer's output in another's context. The assessor and summary are two more sub-tasks, in sequence. If it cannot, run single mode and record mode: single (fallback: no isolated sub-agent primitive) in findings.md so the report says so. Do not emulate independence by role-playing three reviewers in one context: that is one reviewer with three hats, and the report would overstate it.

Looping primitive

Most runtimes have no loop primitive (Claude Code is the exception). In increasing order of automation:

  1. Manual: re-invoke /pr-reviewer <num> after each round until converged: true or --rounds=N.
  2. Task phrasing: "Run /pr-reviewer <num> --rounds=3 repeatedly until findings.md records converged: true for the current revision."
  3. External shell driver:
    for i in $(seq 1 3); do
      <agent-invocation> "/pr-reviewer <num> --rounds=3"
      awk '/^## Revision/{c=0} /^- converged: true$/{c=1} END{exit !c}' "<base-dir>/findings.md" && break
    done

The awk resets at every ## Revision header, so only the latest revision's convergence stops the loop. Always pass --rounds=N; an invocation that finds the cap already reached renders the report without running a pass.

Posting

Step 11 of the skill, after the report, with explicit confirmation, through whatever the runtime offers. Without a posting path, print the report and let the user post it.

LICENSE

README.md

tile.json