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

Project-Grounded Point of View

by EveryInc in EveryInc/compound-engineering-plugin

Forms a decisive, evidence-based verdict on an external tool, a document or a set of approaches for your project, optionally reconciling other models' opinions.

MITAuto-check passedAgent Workflows

Install Project-Grounded Point of View

skills CLI
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-pov -a claude-code

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

GitHub CLI
$ gh skill install EveryInc/compound-engineering-plugin ce-pov --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/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ce-pov .claude/skills/ce-pov && 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
ce-pov
GitHub stars
25k
Token cost
~1.9k tokens
SKILL.md length
1,091 words
Files
16 (incl. scripts, references)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Forms a decisive, evidence-based verdict on an external tool, a document or a set of approaches for your project, optionally reconciling other models' opinions.

  • Works in 5 steps: Frame and Classify → Ground → Verify Grounding → …
  • Deciding whether to adopt an outside library, tool or practice for this project
  • SKILL.md covers Grounding is not optional, Consumer and interaction, Identify the question and… and Artifact Root
  • Runs Shell and Python scripts from its folder; calls git

What it does

The agent delivers a graded verdict on an external-adoption question, a holistic take on a document, or a position on a supplied set of approaches, all measured against the project's own context. It stays read-only and will not issue a view it has not earned. Every subject must meet a minimum project-evidence floor, adoption verdicts must also meet an external evidence bar, and outside claims that a document's conclusion depends on are checked against sources.

The result leads with the decision and keeps the evidence, tradeoffs, uncertainty and deciding conditions, shaped for whoever will use it. If missing information would change the recommendation and cannot be found, the agent returns a Blocked, missing context result instead of interviewing you. An oracle panel option consults other models and reconciles their opinions, backed by `cross-model-pov.sh` and `peer-job-runner.py`, and reference agents scout external evidence, project grounding and precedent. ce-bakeoff, ce-ideate, ce-brainstorm, ce-explain and ce-doc-review cover neighboring jobs.

When your agent uses it

  • Deciding whether to adopt an outside library, tool or practice for this project
  • Getting a holistic judgment on a design document against project constraints
  • Choosing among a supplied set of approaches
  • Consulting other models through an oracle panel and reconciling their views

Example prompts

  • “Should we adopt Temporal for job orchestration? Judge it against how this repo works today.”
  • “Give me your overall take on docs/plans/search-redesign.md.”
  • “Here are three caching approaches. Which one fits our constraints?”
  • “Convene an oracle panel on whether we should move to a monorepo.”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Frame and Classify
  2. Ground
  3. Verify Grounding
  4. Point of View
  5. Deliver and return

What it can do on your machine

Read from SKILL.md and the folder at commit 67035e9. 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

    Ships 2 files in scripts/ (Shell and Python), which the agent can run.

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Project-Grounded Point of View loads about 1.9k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 1,091 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~22k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from EveryInc/compound-engineering-plugin at commit 67035e9, republished under its MIT licence (© EveryInc). 1,091 words, ~1,941 tokens.

Download SKILL.mdSave it as .claude/skills/ce-pov/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.
name
ce-pov
description
Judge a supplied subject against the project's evidence and constraints. Use when assessing an external-adoption question, a holistic take on a document, or a supplied approach set. Use for an oracle panel to consult other models and reconcile their opinions. Use ce-explain for understanding and ce-doc-review for findings review.
argument-hint
[question, document, or approaches] [cross-check] — or bare

Form a Point of View

Produce a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a supplied approach set. The subject is whatever this skill was invoked with, in the prompt or the conversation. Stay read-only while forming and reconciling the POV. You are done when the POV is delivered with its attribution and required disclosure, or when an explicit blocker is returned. Use ce-bakeoff to develop competing solutions, ce-ideate to explore opportunities, or ce-brainstorm to establish goals. The year is 2026, for source recency.

Grounding is not optional

Never issue a POV you did not earn against the project's own context. Every subject must meet the minimum project evidence (the project floor) in references/method.md. An external-adoption verdict must also meet the full external evidence bar there. A document or approach-set POV must verify against outside sources any external claim its bottom line depends on. Nothing the conversation asserts substitutes for grounding.

Consumer and interaction

Deliver a supported position in the form the intended consumer can use. Lead with the decision and preserve the evidence, material tradeoffs, uncertainty, and conditions that determine it. Make identifiers understandable without requiring the reader to reopen the subject. A person's request may need a brief answer or a shareable document; another workflow may need a decision embedded in its own work.

When contributing to an ongoing workflow, return the result and leave continuation to its owner, the calling workflow. Do not add follow-up or panel offers to that return. An explicit oracle or named-peer request still runs the panel, including when it comes from a calling workflow.

Identify the question and return the result

Identify the question from the request and conversation, then look up facts you can verify. Do not interview the user to work out what to assess. If missing information would change the recommendation and you cannot find it, return Blocked — missing context. Explain what is missing, why it matters, and what would resolve it. The calling agent decides whether to ask for clarification or take another action. This applies whether the user invokes ce-pov directly or another agent calls it; no separate non-interactive mode is needed.

Artifact Root

Resolve <root> the first time you compose a <root>/ path; a read of <root>/solutions/ counts as composing one. Pass the resolved path to scouts, never the config. A non-git project has no <root>, so its prior-decision scan uses local ADRs and design docs instead.

<!-- ce-docs-root:start -->

Resolve the CE artifact root <root> before composing any artifact path.

  • Read docs_root from <repo-root>/.compound-engineering/config.yaml only (<repo-root> = git rev-parse --show-toplevel). Do not read it from config.local.yaml. Unset -> <root> is docs, exactly as before.
  • Validate a set value: a repo-relative directory whose real, symlink-resolved path stays inside the repo and is neither the repo root nor under .git/. Otherwise stop with an error naming docs_root and the value -- never fall back to docs.
  • Use <root> as the sole artifact location: create it if absent, compose each path as <root>/<subdir> with this skill's own subdirectory, and never also read docs.
<!-- ce-docs-root:end -->
Phase 0: Frame and Classify

Read references/intake.md now, before any grounding. It defines the output mode, what a calling workflow passes in, orientation and framing, sizing, and what to do when the question has no bounded answer. Settle the subject and the POV intent there (adopt / migrate / compare / is-this-our-problem / Document-take / Approach-set / explainer); an intent that belongs to another skill finishes at intake, and one that continues records how reversible the decision is. Read references/boundaries.md when this skill's fit is in doubt.

Show full SKILL.md (491 more words)Show less
Phase 1: Ground

Read references/grounding.md now, before grounding by either path. It defines the model tiers (the POV reasoning itself is never dispatched), where scratch files may go, what scouts receive and how many run, which capabilities gate which steps, and how grounded facts are kept apart from unconfirmed ones.

Send scouts directly to candidate-specific current evidence, never a generic repo profile. They search in their own context and return a dossier path plus a gist, which you read on demand. Where the facts the verdict depends on are already located, confirm them with bounded reads of the authoritative source instead of dispatching scouts; unscoped or noisy grounding still dispatches. A claim made in the conversation is a pointer to check, never self-verifying. The prior-decision scan (<root>/solutions/, ADRs, design docs) stays mandatory on either path.

When the judgment requires an explanation of unresolved behavior or design rationale, invoke ce-explain. Pass the question, its scope, and the decision it informs. Use adequate current evidence instead of repeating an investigation. Treat its cited findings as evidence to assess under the same grounding standard, not as authority for the recommendation. Keep ownership of the judgment here. If ce-explain is unavailable, gather the evidence directly or report what is missing.

Phase 2: Verify Grounding

Read references/method.md now, before reasoning about the POV. It defines the Verify and POV steps, the skeptic stance, tiering, and the evidence check. Apply that check over the grounded evidence. If the evidence falls short, no subject shape may return a confident result; that reference names the result each shape returns instead.

Phase 3: Point of View

First form ce-pov's own independent POV under the active subject-shape contract in references/method.md, but do not emit it. Freeze that position. Keep it out of an independent peer's initial context; expose it only when the task is to critique that position, or in a later reconciliation round.

A panel request is an explicit ask to consult or reconcile other models: a panel, a cross-check, or oracle, anywhere in the invocation context. Declining one, or merely mentioning one, is not a request. When a panel is requested, or when a POV formed without one may qualify for a proactive offer, read references/cross-model-panel.md before resolving participation or deciding whether to offer. Finish the panel branch before composing the result. A POV that follows a panel request states which peers ran, or that none did and why. A POV with no panel request carries no panel note.

Only then deliver the position with the content required by references/method.md. Adapt its presentation to the intended use; cite supporting evidence rather than reprinting dossiers or raw peer output.

Phase 4: Deliver and return

The judgment is the deliverable; implementation is not. A calling workflow receives the result and control back. For a requested write-up or continuation, read references/followup.md; it defines artifact delivery and what authority a downstream action needs. Do not require a next-step choice to complete a POV.

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

Files

SKILL.md and 15 other files (scripts, references) in skills/ce-pov of EveryInc/compound-engineering-plugin.

  • SKILL.md
  • references/agents/external-evidence-researcher.md
  • references/agents/pov-peer.md
  • references/agents/precedent-activity-scout.md
  • references/agents/project-grounding-scout.md
  • references/boundaries.md
  • references/cross-model-panel.md
  • references/followup.md
  • references/grounding.md
  • references/intake.md
  • references/invocation.md
  • references/method.md
  • references/pov-schema.json
  • references/report.md
  • scripts/cross-model-pov.sh
  • scripts/peer-job-runner.py

Open the folder on GitHubat commit 67035e9

Compare with similar skills

Project-Grounded Point of View 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.

Project-Grounded Point of View compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Project-Grounded Point of View this skillEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT
Architect Before Implementingcursor/plugins10k8 repos~1.4kAutomated safety check: PassNone
GitHub Multi-Repo Coordinationruvnet/agentic-flow8195 repos~5.6kAutomated safety check: PassNone
Orca CLIstablyai/orca88k2 repos~593Automated safety check: PassMIT
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Paseo Committeegetpaseo/paseo20k1 repos~496Automated safety check: PassCustom licence

Similar skills

  • Architect Before Implementing

    cursor/plugins

    Official

    Sketches types, signatures and module boundaries with stub bodies before real code, compares at least two designs, then implements against the chosen sketch.

    10k GitHub starsUsed in 8 repos~1.4k tokens
    DevelopmentAuto-check passed

  • GitHub Multi-Repo Coordination

    ruvnet/agentic-flow

    Coordinates work across several GitHub repositories: swarm-driven cross-repo operations, package version and documentation sync, and repository structure optimization.

    819 GitHub starsUsed in 5 repos~5.6k tokens
    DevelopmentAuto-check passed

  • Orca CLI

    stablyai/orca

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

    88k GitHub starsUsed in 2 repos~593 tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Paseo Committee

    getpaseo/paseo

    Forms a two-agent committee with contrasting profiles to analyze a stuck problem in parallel, reconcile their views and return a consensus plan without editing files.

    20k GitHub starsUsed in 1 repo~496 tokens
    Agent WorkflowsAuto-check passed

  • Context Mode Ops

    mksglu/context-mode

    Runs maintenance for the context-mode project with parallel subagents: issue triage, PR review, releases, bug fixes, announcements and branch syncing.

    26k GitHub stars~6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from EveryInc/compound-engineering-plugin

All 37 skills in this repo

  • Compound Learning Writer

    EveryInc/compound-engineering-plugin

    Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Compound Learnings Refresh

    EveryInc/compound-engineering-plugin

    Audits a repo's stored learnings against the current codebase, fixes stale, overlapping or superseded docs and reports on every document.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Compound Engineering Prototype

    EveryInc/compound-engineering-plugin

    Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed.

    25k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Compound Engineering Setup

    EveryInc/compound-engineering-plugin

    Checks Compound Engineering plugin health and repo-local config, or scaffolds a Compound Pack when you ask for one by id.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • PR Babysitter

    EveryInc/compound-engineering-plugin

    Watches an open GitHub pull request over time, routing review comments and CI failures to other skills until the PR is ready to merge.

    25k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • CE Brainstorm

    EveryInc/compound-engineering-plugin

    Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

    25k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Project-Grounded Point of View

What does Project-Grounded Point of View do?

Forms a decisive, evidence-based verdict on an external tool, a document or a set of approaches for your project, optionally reconciling other models' opinions. The agent delivers a graded verdict on an external-adoption question, a holistic take on a document, or a position on a supplied set of approaches, all measured against the project's own context. It stays read-only and will not issue a view it has not earned.

When should I use Project-Grounded Point of View?

Project-Grounded Point of View fits situations like: deciding whether to adopt an outside library, tool or practice for this project; getting a holistic judgment on a design document against project constraints; choosing among a supplied set of approaches; consulting other models through an oracle panel and reconciling their views.

How do I install Project-Grounded Point of View in Claude Code?

Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-pov -a claude-code`. Or copy the skill folder (skills/ce-pov in EveryInc/compound-engineering-plugin) into .claude/skills/ce-pov in your project. Claude Code loads it when a task matches its description.

How do I install Project-Grounded Point of View in Codex?

Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-pov -a codex`. Or copy the skill folder (skills/ce-pov in EveryInc/compound-engineering-plugin) into .agents/skills/ce-pov in your project. Codex loads it when a task matches its description.

Can I use Project-Grounded Point of View 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 EveryInc/compound-engineering-plugin --skill ce-pov -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ce-pov, .gemini/skills/ce-pov, .github/skills/ce-pov and .opencode/skills/ce-pov in your project.

What does Project-Grounded Point of View need to run?

Going by SKILL.md and its folder, Project-Grounded Point of View needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (git).

Does Project-Grounded Point of View access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Project-Grounded Point of View 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Project-Grounded Point of View use?

Project-Grounded Point of View 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 Project-Grounded Point of View use?

About 1.9k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 20k tokens, read only when the agent opens those files.

What are the alternatives to Project-Grounded Point of View?

Skills that share tags, products or a category with Project-Grounded Point of View: Architect Before Implementing (cursor/plugins, 10k stars), GitHub Multi-Repo Coordination (ruvnet/agentic-flow, 819 stars), Orca CLI (stablyai/orca, 88k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Project-Grounded Point of View?

EveryInc (a GitHub organization) maintains it in EveryInc/compound-engineering-plugin, which has 25,436 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 8, 2026.

Source: EveryInc/compound-engineering-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.