Skip to content
Skills Library
Management & product · Review & audit

gap-analysis

/gap-analysis

Use to find what's missing — spec → implementation gaps, target → actual gaps, intended-vs-built. Produces a gap inventory with severity and effort estimates.

Repository
sift-coder ↗
Licence
MIT
Last repository change
03.06.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 03.06.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use to find what's missing — spec → implementation gaps, target → actual gaps, intended-vs-built. Produces a gap inventory with severity and effort estimates.

Original author description

Use to find what's missing — spec → implementation gaps, target → actual gaps, intended-vs-built. Produces a gap inventory with severity and effort estimates.

How it works

  1. Method
  2. Output shape
  3. Rules
  4. Anti-patterns
  5. When NOT to use
  6. Subagent dispatch
  7. Value over native CC
Original SKILL.md headings · 85 lines, 378 words
SKILL.md preview
---
name: gap-analysis
description: Use to find what's missing — spec → implementation gaps, target → actual gaps, intended-vs-built. Produces a gap inventory with severity and effort estimates.
---

# gap-analysis

What was promised vs what was built. What was intended vs what exists. Surface gaps with severity + effort.

## Method

1. **Establish target.** What's the reference? Possible inputs:
   - Spec doc
   - Acceptance criteria checklist
   - Architecture doc / diagram
   - Test plan
   - Prior implementation in another repo (for migration)
2. **Establish actual.** What exists?
   - Code present
   - Tests present
   - Docs present
   - Operational / monitored
3. **Match item-by-item.**
   - **Present** ✅
   - **Partial** ⚠️ (exists but incomplete or buggy)
   - **Missing** ❌
4. **Severity per gap:**
   - **Blocker** — capability unavailable
   - **High** — capability degraded
   - **Medium** — secondary functionality
   - **Low** — nice-to-have
5. **Effort estimate** per gap (hours or days).

## Output shape

```
Target:    <spec/doc/checklist source>
Actual:    <repo / branch / deploy>

Coverage:  ✅ N  ⚠️ M  ❌ K  (out of N+M+K total items)

Gaps:

  ❌ [BLOCKER]   <item>  
                  Target says: <quote>
                  Actual:      <evidence of absence>
                  Effort:      <hrs/days>

  ⚠ [HIGH]      <item>
                  Target says: <quote>
                  Actual:      <partial impl at file:line>
                  Effort:      <hrs/days>

  ⚠ [MEDIUM]    <item>
                  ...

Total effort to close gaps: <hrs/days>
```

## Rules

- **Cite both sides.** Target quote + actual evidence (or "not found in <searched paths>").
- **Don't conflate "not yet built" with "not designed".** Flag the latter as a target ambiguity.
- **Severity by capability impact, not effort.** Easy fix can still be a blocker.
- **Search broadly before declaring missing.** Capability may be implemented under a different name.

## Anti-patterns

- Counting tests as items (separate analysis)
- Marking partial as missing (or vice versa) without evidence
- Effort estimates without scope (always say what's in the estimate)
- Ignoring "extra" — items in actual that aren't in target (might be rot or prudent additions)

## When NOT to use

- No clear target reference — gap-analysis needs both sides
- Pre-spec stage — `/improve-spec` first
- Ongoing development — wait for a milestone

## Subagent dispatch

- `Explore` to map actual
- `general-purpose` for the matching pass
- Memory MCP for what was decided in prior sessions

## Value over native CC

CC will compare two things if asked. CC won't naturally produce structured target ↔ actual matrix with severity + effort columns. The structure IS the value — feeds into prioritisation.

Versions

RepositoryScoreLicence
This page · ialameh/sift-coder100MIT
anassahel/agent-labs100MIT
magnus919/agent-skills100MIT
richardochristjia/skills100MIT
kael-odin/codex-plugins-zh100MIT
afonsoft/skills100MIT
adeerkhan/vitruvius100MIT
qa-aman/claude-skills100MIT
testdouble/han100MIT

Database snapshot: 13.11.2026 · package version ac81e10c6538 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100okhp3-process-gap-analysis
    Identify deviations, gaps, and exception paths between an as-is process capture and its intended design. Use this skill when the user wants to find where a process breaks down, where steps are missing or inconsistent, where exception handling is undefined, or where current…
  • 100om-pre-implement-spec
    Analyze a spec before implementation: BC audit, risk assessment, gap analysis. Produces a readiness report with BC violations, missing sections, and suggested improvements. Triggers on \"analyze spec\", \"pre-implement\", \"spec readiness\", \"BC analysis\", \"spec gap analysis\".
  • 90analysing-gaps-and-impacts
    Produces gap analyses (existing vs target, as-is / to-be, analyse de l'existant et de la cible) and impact analyses (analyse d'impact) for a change, a new regulation, a migration or a new product - impacts on processes, applications, data, interfaces, organisation and people,…
  • 100pm-gap-analysis
    Run a Pragmatic Institute Gap Analysis — a market-driven self-assessment of how well the team performs the 37 activities of the Pragmatic Framework, who owns each, and where the biggest gaps are. Use when the PM asks "where do we stand", "how are we doing on the framework", a…
  • 100okhp3-process-gap-exception-analysis
    Identify deviations, gaps, and exception paths between an as-is process capture and its intended design. Use this skill when the user wants to find where a process breaks down, where steps are missing or inconsistent, where exception handling is undefined, or where current…
  • 100prd-review
    Use when a PRD exists (file, paste, URL) and needs gap analysis. Dispatches PM, agile-coach, tech-lead, DX, cost reviewer agents in parallel against a 13-dimension rubric; produces scored summary with severity-tiered gaps and P0-gated verdict. Triggers on /prd-review, review my…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.