CtrlK
BlogDocsLog inGet started
Tessl Logo

migrate-content-ia

Handle Hugo docs information-architecture moves: discover old vs new URLs, add front matter aliases (Phase 1), update in-repo links (Phase 2), interactive List 2 resolution and fragment validation (Phase 3; no guessing). Supports PR-scoped mapping plus whole-content sweeps for inbound links to that mapping, or a full-site follow-up. Triggers on: "IA migration", "redirects for moved pages", "fix links after content move", "PR-scoped link/anchor pass", "aliases for old URLs". After branch work, chain the review-changes skill (main...HEAD) before a PR. Agents must run the in-file required procedure and definition of done, not the phases alone in isolation.

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body has excellent workflow sequencing with explicit validation and feedback loops, and its commands are concrete. Its main weaknesses are verbosity from repeating the same rules across sections and limited use of progressive disclosure, with much detail kept inline rather than split into reference files.

Suggestions

Consolidate the PR-scoped-vs-sweep and no-guessing rules into single authoritative sections and reference them instead of restating them in Modes, Phase 0.5, Phase 2, and Phase 3.

Move the detailed Conventions (aliases, links, shortcodes, fragments, external URLs, special cases) into a separate reference.md linked from the body, leaving SKILL.md as a lean overview of the required procedure and phases.

Add concrete, copy-paste-ready examples of the actual List 1 and List 2 link edits (before/after diff snippets) so the core editing actions are executable rather than described in prose.

DimensionReasoningScore

Conciseness

The body is thorough and mostly domain-specific policy Claude would not know, but key rules are restated multiple times (the PR-scoped-vs-sweep distinction recurs in the procedure, Modes, Phase 0.5, Phase 2 and Phase 3; "no guessing" repeats in four places), so it could be tightened. It is not level 1 because the content is genuine project policy rather than generic concepts Claude already knows.

2 / 3

Actionability

It provides concrete executable commands (git diff --name-only main...HEAD, merge-base then diff, docker buildx bake validate) and a real scope-pr-files.sh helper, but the core link-edit steps are described as prose ("Replace old source paths... preserve each file's link pattern") rather than given as copy-paste-ready commands. It is not level 3 because the central editing actions are not fully executable code.

2 / 3

Workflow Clarity

The multi-step process is explicitly sequenced (Phases 0→0.5→1→2→3 plus a mandatory "Run in order" list) with a validation checkpoint (docker buildx bake validate), a re-sweep feedback loop ("re-print or re-scan for List 2 until empty or deferred"), and a Definition-of-done checklist, matching the anchor for clear sequence with explicit validation and feedback loops.

3 / 3

Progressive Disclosure

There is one real bundle file (scripts/scope-pr-files.sh) referenced correctly and a convention for an optional reference.md, with no deeply nested references; however the detailed Conventions and Phase sections remain inline in a ~370-line SKILL.md rather than being split into well-signaled one-level-deep reference files. It is not level 1 because sections are headed and organized, and not level 3 because content that could be separate is left inline.

2 / 3

Total

9

/

12

Passed

Description

100%

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 states concrete phase-scoped actions, provides an explicit natural-language trigger list, and carves out a distinctive niche. It fully satisfies the what-and-when bar without vague fluff or first/second-person voice.

DimensionReasoningScore

Specificity

Multiple concrete actions are named ("discover old vs new URLs", "add front matter aliases", "update in-repo links", "interactive List 2 resolution and fragment validation"), matching the anchor for listing several specific concrete actions rather than naming only a domain and some actions.

3 / 3

Completeness

It clearly answers both what (the phase-based actions) and when (the explicit "Triggers on:" list), matching the anchor for clearly answering both what AND when with explicit triggers rather than having when only implied.

3 / 3

Trigger Term Quality

An explicit "Triggers on:" clause lists five natural phrases a user would say ("IA migration", "redirects for moved pages", "fix links after content move", "PR-scoped link/anchor pass", "aliases for old URLs"), giving good coverage rather than only some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow and domain-specific (Hugo docs IA moves, front matter aliases, redirect/list-2/fragment handling) with distinct triggers, making it unlikely to fire for an unrelated skill; not merely somewhat specific with overlap.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
docker/docs
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.