@hamzafarooq/feature-prioritizer
AScore a feature list using RICE (Reach, Impact, Confidence, Effort) and return a ranked table with recommendation. Use when the user wants to prioritize features, decide what to build next, or cut scope.
Install
agr install @hamzafarooq/feature-prioritizer --target claudeWrites 1 file into .claude/skills/, pinned to git-ad8d2996.
- .claude/skills/feature-prioritizer/SKILL.md
Document
name: feature-prioritizer description: Score a feature list using RICE (Reach, Impact, Confidence, Effort) and return a ranked table with recommendation. Use when the user wants to prioritize features, decide what to build next, or cut scope.
Ask the user:
- "Paste your list of features or initiatives."
- "What's the timeframe — one quarter, one sprint, one year?"
- "Any features that are already committed or non-negotiable? I'll mark them separately."
For each feature, estimate:
- Reach — how many users affected per period (1–10 scale or absolute number)
- Impact — how much does it move the needle per user (0.25 = minimal, 0.5 = low, 1 = medium, 2 = high, 3 = massive)
- Confidence — how sure are you about Reach and Impact? (percentage: 50%, 80%, 100%)
- Effort — person-months to build (use your best estimate; flag if unclear)
RICE score = (Reach × Impact × Confidence) / Effort
Feature Prioritization — [Product / Quarter]
| Feature | Reach | Impact | Confidence | Effort | RICE Score | Priority |
|---|---|---|---|---|---|---|
| [feature] | [#] | [#] | [%] | [months] | [score] | HIGH/MED/LOW |
Recommended build order
Top 3 features with one-line rationale for each.
Features to cut or defer
Which items scored low and why you should drop or delay them.
What the scores can't tell you
Flag 1–2 strategic or political factors that aren't captured in RICE but matter for the decision.
State your assumptions clearly. Ask: "Want me to re-score with different estimates?"
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-ad8d2996d5d82026-07-31