New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Spectre Scope

by joenandez in joenandez/spectre

Scope a feature or improvement into explicit IN / OUT / ANTI-SCOPE boundaries before planning or code — grounds a hypothesis in repo reality, resolves blocking questions, and writes scope.md.

MITAuto-check passed

Install Spectre Scope

skills CLI
$ npx skills add joenandez/spectre --skill spectre-scope -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install joenandez/spectre spectre-scope --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/joenandez/spectre.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/spectre/skills/spectre-scope .claude/skills/spectre-scope && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
spectre-scope
GitHub stars
164
Token cost
~1.5k tokens
SKILL.md length
694 words
Files
1
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Scope a feature or improvement into explicit IN / OUT / ANTI-SCOPE boundaries before planning or code — grounds a hypothesis in repo reality, resolves blocking questions, and writes scope.md.

  • Works in 9 steps: The Problem — pain, impact, current state → Target Users — primary, secondary, needs → Success Criteria — measurable assertions… → …
  • Technical design/research (spectre-plan)
  • SKILL.md covers Inputs, Working Set (late-bound — read…, Feature root contract and Method / guardrails, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Spectre Scope is an agent skill from joenandez/spectre. Scope a feature or improvement into explicit IN / OUT / ANTI-SCOPE boundaries before planning or code — grounds a hypothesis in repo reality, resolves blocking questions, and writes scope.md. Trigger for new or fuzzy work or re-scoping. Do NOT trigger for technical design/research (spectre-plan) or standalone bug diagnosis (spectre-fix).

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Spectre is a battle-tested 6 stage agentic engineering workflow for building complex, production-ready features. You stay in the loop for the decisions that matter. Your agents…. The licence is MIT.

When your agent uses it

  • Technical design/research (spectre-plan)
  • Standalone bug diagnosis (spectre-fix)

Example prompts

  • “/spectre-scope”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. The Problem — pain, impact, current state
  2. Target Users — primary, secondary, needs
  3. Success Criteria — measurable assertions over prose
  4. User Experience — journeys, principles, trade-offs
  5. Scope Boundaries — IN / OUT / ANTI-SCOPE / Maybe / Future
  6. Load-Bearing Assumptions — each with a short "if this is false, …" consequence
  7. Constraints — platform/perf/a11y/scale (user-provided only)
  8. Decisions — choices + rationale
  9. Risks — UX, scope creep, open questions

What it can do on your machine

Read from SKILL.md and the folder at commit 931c9e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Spectre Scope loads about 1.5k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 694 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from joenandez/spectre at commit 931c9e8, republished under its MIT licence (© joenandez). 694 words, ~1,525 tokens.

Download SKILL.mdSave it as .claude/skills/spectre-scope/SKILL.md (or your agent's skills folder).
name
spectre-scope
description
Scope a feature or improvement into explicit IN / OUT / ANTI-SCOPE boundaries before planning or code — grounds a hypothesis in repo reality, resolves blocking questions, and writes scope.md. Trigger for new or fuzzy work or re-scoping. Do NOT trigger for technical design/research (spectre-plan) or standalone bug diagnosis (spectre-fix).
user-invocable
true

scope

Turn an unstructured request into clear scope boundaries (IN / OUT / ANTI-SCOPE), user value, load-bearing assumptions, and decisions — clear on WHAT, silent on HOW. Boundaries and user value first; defer all technical/implementation questions to /spectre:spectre-plan.

Inputs

  • $ARGUMENTS — the feature/problem brain-dump. If empty → greet, ask for context, and WAIT for the user.
  • Existing root/artifact: context for new work; reuse only for the same scope run, FROM_KICKOFF=true, or explicit resume/re-scope. On re-scope, read concepts/scope.md fully, surface settled decisions and the delta, and confirm before rewriting the immutable downstream anchor.
  • FROM_KICKOFF=true + KICKOFF_DOC → read the doc, extract (Core Problem, User Value, Decisions Made, Remaining Ambiguities, Key Code Refs), then skip grounding + exploration and go straight to clarifications. Already-grounded.

Working Set (late-bound — read at run-time, never inline)

  • FEATURE_ROOT = .spectre/features/<feature-name>/, resolved from the input or proposed below.
  • captured session or current thread memory for this area, if present
  • Reuse current-request knowledge results/loads; otherwise follow Project knowledge routing. Search actual task across mixed knowledge/work previews; assess, then exact-load applicable records. Standalone #tag: exact search --tag, assess previews, then exact-load applicable matches; never guessed loads. Refine only for an unresolved question or new subject. Keep IDs/revisions in concepts/scope.md; previews/unloaded candidates are not evidence.

Feature root contract

  • Reuse a managed FEATURE_ROOT only when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and follow @skill-spectre:spectre-feature-root through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged.

Method / guardrails

  • Reply before tools. Acknowledge first; never go silent to "think." No tool calls in the opening reply except reading KICKOFF_DOC when FROM_KICKOFF=true.
  • WHAT, not HOW. Ask only about boundaries, user value, and anti-scope. Defer architecture/trade-offs/integration to /spectre:spectre-plan. Exception: scope that is inherently technical (e.g. "migrate DB X→Y").
  • Ground once. Start with exactly one fast lookup to anchor the hypothesis in repo reality — a single @spectre:finder query, or one grep/glob; skip it if slow. Needing broader grounding exceeds this fast scope pass.
  • Use knowledge before affected decisions. Discovery is per question, not skill: never repeat an equivalent query merely because Scope began. A work body answers only a stated question, including a potentially critical imported constraint without a maintained equivalent. Do not reload an unchanged revision already in context; workers receive compact applicable findings and provenance, never record bodies.
  • Lead with a grounded hypothesis (problem, who it affects, proposed feature name/root, IN / OUT / ANTI-SCOPE) and 5–8 questions tagged (blocking) / (optional). Iterate boundaries (IN / OUT / ANTI-SCOPE / Unsure) until confirmed, then clarify remaining ambiguity with AskUserQuestion (≤4 at a time). No clarification files.
Show full SKILL.md (267 more words)Show less

Outputs + DONE

Write {FEATURE_ROOT}/concepts/scope.md, beginning immediately below the title with Feature: <feature-name> and Feature Root: .spectre/features/<feature-name>, then user value & boundaries before technical detail, with all of:

  1. The Problem — pain, impact, current state
  2. Target Users — primary, secondary, needs
  3. Success Criteria — measurable assertions over prose
  4. User Experience — journeys, principles, trade-offs
  5. Scope Boundaries — IN / OUT / ANTI-SCOPE / Maybe / Future
  6. Load-Bearing Assumptions — each with a short "if this is false, …" consequence
  7. Constraints — platform/perf/a11y/scale (user-provided only)
  8. Decisions — choices + rationale
  9. Risks — UX, scope creep, open questions
  10. Next Steps — recommended command + complexity S/M/L

ANTI-SCOPE ≠ OUT. OUT = not building it (yet/this release). ANTI-SCOPE = a problem we are intentionally not solving — the philosophical edge of what the feature is for. Both are required.

DONE when: scope.md exists with all 10 sections; IN / OUT / ANTI-SCOPE are explicit; every load-bearing assumption carries its "if false" consequence; the user has confirmed the boundaries.

Handoff

HandoffDetails
🧭 Current phaseDone
📦 What was just doneResult
▶️ Proposed next stepRender resolved action.
🔀 AlternativePause: /spectre:spectre-handoff with the resolved feature when stopping.

Present boundaries/assumptions/path; unsettled → Scope; UI load-bearing and journeys, segments, states, copy, or accessibility unresolved → UX; interaction/layout/visual validation materially matters → Prototype; otherwise confirmed repository-changing work → /spectre:spectre-plan. One route/conditional; edits re-route.

Escalate-If

  • Grounding needs more than one lookup, or the request spans several unknowns → this exceeds a fast scope pass; gather context more fully before proceeding.
  • The user pushes for implementation/architecture answers → note them and defer to /spectre:spectre-plan; keep this pass on WHAT.
  • Boundaries won't converge after iterating → surface the specific unresolved tension and ask the user to decide before writing the doc.

© joenandez, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/spectre/skills/spectre-scope of joenandez/spectre.

Open the folder on GitHubat commit 931c9e8

Compare with similar skills

Spectre Scope next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Spectre Scope compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Spectre Scope this skilljoenandez/spectre164—~1.5kAutomated safety check: PassMIT
Skill Improversickn33/agentic-awesome-skills47k2 repos~1.5kAutomated safety check: PassMIT
Improve Oaselastic/kibana21k—~4.8kAutomated safety check: PassCustom licence
Self-Improve Evolutionary LoopYeachan-Heo/oh-my-claudecode40k—~5.3kAutomated safety check: WarnMIT
Anti Reversing Techniqueswshobson/agents40k—~980Automated safety check: PassMIT
Python Anti Patternswshobson/agents40k—~2kAutomated safety check: PassMIT

Similar skills

  • Skill Improver

    sickn33/agentic-awesome-skills

    Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.

    47k GitHub starsUsed in 2 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Improve Oas

    elastic/kibana

    Official

    Add or improve OpenAPI descriptions, examples, and code samples for a Kibana API area.

    21k GitHub stars~4.8k tokensUpdated today
    Backend & APIsAuto-check passed

  • Self-Improve Evolutionary Loop

    Yeachan-Heo/oh-my-claudecode

    Runs an autonomous improvement loop on a repository: agents propose and execute plans, a tournament picks the winner by benchmark, and each round is recorded and plotted.

    40k GitHub stars~5.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: warnings

  • Anti Reversing Techniques

    wshobson/agents

    Understand anti-reversing, obfuscation, and protection techniques encountered during software analysis.

    40k GitHub stars~980 tokensUpdated 5 days ago
    SecurityAuto-check passed

  • Python Anti Patterns

    wshobson/agents

    A skill your agent uses when reviewing Python code for common anti-patterns to avoid.

    40k GitHub stars~2k tokensUpdated 5 days ago
    DevelopmentAuto-check passed

  • Skill Improvement Loop

    Donchitos/Claude-Code-Game-Studios

    Improves a single skill through a test, fix and retest loop, keeping or reverting each change based on how the static and category scores move.

    26k GitHub stars~1.7k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes

More from joenandez/spectre

All 26 skills in this repo

  • Verify Spectre

    joenandez/spectre

    A skill your agent uses when validating that the Spectre plugin itself still works after ANY change to this repo — skills, prompts, agents, hooks, the CLI, the Codex mirror, or a release.

    164 GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed

  • Feature Codex Spectre Implementation

    joenandez/spectre

    A skill your agent uses when modifying the Codex SPECTRE install flow, SessionStart continuity, project skill syncing, registry injection, or Codex-specific runtime files.

    164 GitHub stars~2.2k tokensUpdated 7 days ago
    Auto-check passed

  • Spectre Handoff

    joenandez/spectre

    Save a quiet, branch-keyed session snapshot with continuity, active work, and optional task/todo state for automatic resume.

    164 GitHub stars~1.3k tokensUpdated 7 days ago
    Auto-check passed

  • Spectre Learn

    joenandez/spectre

    User-invoked front door for durable capture. An agent skill from joenandez/spectre.

    164 GitHub stars~1k tokensUpdated 7 days ago
    Auto-check passed

  • Spectre Rewrite Skill

    joenandez/spectre

    Rewrite a verbose SPECTRE skill into a compact, contract-form Spectre skill proposal — clear on WHAT, silent on HOW — grounded in the spectre-light distillation and freedom-tier budget.

    164 GitHub stars~3k tokensUpdated 7 days ago
    Auto-check passed

  • Spectre Rewrite Subagent

    joenandez/spectre

    Rewrite Spectre subagent definitions into compact, contract-driven agents with clear routing, least-privilege tools, output schemas, and an auditable rewrite trail.

    164 GitHub stars~1.8k tokensUpdated 7 days ago
    Auto-check passed

Questions about Spectre Scope

What does Spectre Scope do?

Scope a feature or improvement into explicit IN / OUT / ANTI-SCOPE boundaries before planning or code — grounds a hypothesis in repo reality, resolves blocking questions, and writes scope.md. Spectre Scope is an agent skill from joenandez/spectre.md.

When should I use Spectre Scope?

Spectre Scope fits situations like: technical design/research (spectre-plan); standalone bug diagnosis (spectre-fix).

How do I install Spectre Scope in Claude Code?

Run `npx skills add joenandez/spectre --skill spectre-scope -a claude-code`. Or copy the skill folder (plugins/spectre/skills/spectre-scope in joenandez/spectre) into .claude/skills/spectre-scope in your project. Claude Code loads it when a task matches its description.

How do I install Spectre Scope in Codex?

Run `npx skills add joenandez/spectre --skill spectre-scope -a codex`. Or copy the skill folder (plugins/spectre/skills/spectre-scope in joenandez/spectre) into .agents/skills/spectre-scope in your project. Codex loads it when a task matches its description.

Can I use Spectre Scope in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add joenandez/spectre --skill spectre-scope -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spectre-scope, .gemini/skills/spectre-scope, .github/skills/spectre-scope and .opencode/skills/spectre-scope in your project.

What does Spectre Scope need to run?

SKILL.md names no scripts, command-line tools or credentials: Spectre Scope is instructions for the agent only.

Does Spectre Scope access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Spectre Scope safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Spectre Scope use?

Spectre Scope is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Spectre Scope use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Spectre Scope?

Skills that share tags, products or a category with Spectre Scope: Skill Improver (sickn33/agentic-awesome-skills, 47k stars), Improve Oas (elastic/kibana, 21k stars), Self-Improve Evolutionary Loop (Yeachan-Heo/oh-my-claudecode, 40k stars) and Anti Reversing Techniques (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Spectre Scope?

joenandez (a GitHub user) maintains it in joenandez/spectre, which has 164 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 2, 2026.

Source: joenandez/spectre on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.