CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-stack

Managing stacked/dependent pull requests with GitHub

71

2.02x
Quality

57%

Does it follow best practices?

Impact

95%

2.02x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./dot_config/opencode/skill/pr-stack/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

22%

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 too terse and vague, providing only a high-level topic ('Managing stacked/dependent pull requests') without specifying concrete actions or when the skill should be triggered. While the domain is somewhat niche (stacked PRs), the lack of specificity and explicit trigger guidance significantly weakens its utility for skill selection among many options.

Suggestions

Add specific concrete actions such as 'Creates stacked PR chains, rebases dependent branches, updates PR descriptions with stack status, and resolves merge conflicts across dependent PRs'.

Add an explicit 'Use when...' clause, e.g., 'Use when the user mentions stacked PRs, PR chains, dependent branches, cascading pull requests, or needs to rebase a series of dependent PRs on GitHub'.

Include common natural trigger terms and variations like 'PR stack', 'PR chain', 'dependent branches', 'rebase stack', 'cascading PRs', and 'branch dependencies'.

DimensionReasoningScore

Specificity

The description uses vague language ('Managing') without listing any concrete actions. It doesn't specify what managing entails—e.g., creating, rebasing, updating, resolving conflicts in stacked PRs.

1 / 3

Completeness

The description only vaguely addresses 'what' (managing stacked PRs) and completely lacks any 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1.

1 / 3

Trigger Term Quality

It includes some relevant keywords like 'stacked', 'dependent', 'pull requests', and 'GitHub' that users might naturally say. However, it misses common variations like 'PR chain', 'PR stack', 'rebase dependent PRs', 'cascading PRs', or 'branch dependencies'.

2 / 3

Distinctiveness Conflict Risk

The mention of 'stacked/dependent pull requests' provides some specificity that distinguishes it from generic GitHub or PR skills, but without concrete actions it could still overlap with general GitHub PR management skills.

2 / 3

Total

6

/

12

Passed

Implementation

92%

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

This is a strong, well-structured skill that efficiently covers the full lifecycle of stacked PR management with git-spice. Commands are concrete and executable, workflows are clearly sequenced with safety checkpoints, and the content respects Claude's intelligence by avoiding unnecessary explanations. Minor improvement could come from better signaling of external references.

DimensionReasoningScore

Conciseness

Every line is actionable — no explanations of what stacked PRs are, no filler about why git-spice is good. Commands are presented directly with minimal but sufficient annotations.

3 / 3

Actionability

Provides concrete, copy-paste-ready commands for every operation (init, create, submit, sync, merge, manual detection). Includes specific flags like `--squash --delete-branch` and `--force-with-lease`.

3 / 3

Workflow Clarity

Multi-step workflows are clearly sequenced: merge bottom-up then sync, sync pulls trunk then restacks, submit has clear scope variants. Safety section includes validation checkpoints (CI verification, mergeable check, conflict detection) and explicit constraints.

3 / 3

Progressive Disclosure

Content is well-organized into logical sections (Tools, Stack Operations, Manual detection, Safety), but everything is inline in a single file. For a skill of this size (~70 lines), this is acceptable, but the reference to AGENTS.md safety rules and the spice configuration option could benefit from clearer signaling or links.

2 / 3

Total

11

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
athal7/dotfiles
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.