Agent skill

Fix What I Pointed At

by reticlehq in reticlehq/reticle

Picks up bugs a person flagged by pointing at elements in the running app, each mark carrying the element, their note and the source file and line, then fixes and verifies them.

Apache-2.0Auto-check passedDevelopment

Install Fix What I Pointed At

skills CLI
$ npx skills add reticlehq/reticle --skill fix-what-i-pointed-at -a claude-code

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

GitHub CLI
$ gh skill install reticlehq/reticle fix-what-i-pointed-at --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/reticlehq/reticle.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fix-what-i-pointed-at .claude/skills/fix-what-i-pointed-at && 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
fix-what-i-pointed-at
GitHub stars
1.2k
Token cost
~878 tokens
SKILL.md length
397 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

Picks up bugs a person flagged by pointing at elements in the running app, each mark carrying the element, their note and the source file and line, then fixes and verifies them.

  • Works in 5 steps: Read the marks. Group them if several… → Open source.file at source.line. This is… → Fix what the note asks for. If the note… → …
  • Fixing bugs a designer or PM flagged directly in the running app
  • SKILL.md covers Drain the marks, The loop, When you cannot fix one and Report back in their vocabulary
  • Calls npx and curl; reaches docs.reticle.sh

What it does

Reticle's running app has a Flag a bug control: a person clicks it, points at an element and types what is wrong. Each flag becomes a mark that carries the element, the note and a file and line pointer, so the usual cycle of screenshot, description and clarifying questions collapses into one call. The skill drains the marks with reticle_session in review mode, at the start of a session and again whenever the person has been in the app. Reading never consumes a mark.

The loop is read, open, fix, verify, resolve. The agent groups marks that point at the same file, opens source.file at source.line, fixes what the note asks, and verifies in the running app by re-driving the control with reticle_act_and_wait or inspecting the element with reticle_look instead of eyeballing it. Only then does it resolve the mark. A mark that cannot be fixed is left open with an explanation, and if a note describes intended behavior, the agent says so and lets the person decide. Reports use the person's wording, such as the Pay button on checkout, instead of file paths.

When your agent uses it

  • Fixing bugs a designer or PM flagged directly in the running app
  • Starting a session on an app someone has been clicking through
  • Resolving a vague report like that button there without knowing the file

Example prompts

  • “I flagged a few things in the app. Pick them up and fix them.”
  • “The spacing on that card is wrong. Check the marks and fix it at the source.”
  • “Review the flagged marks, group the ones in the same file, and resolve each after verifying.”

Requirements

  • The Reticle server and a running app, installed with npx @reticlehq/server init

Workflow steps

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

  1. Read the marks. Group them if several point at the same file: one edit often answers three.
  2. Open source.file at source.line. This is the whole point: no hunting for which component rendered that button.
  3. Fix what the note asks for. If the note is ambiguous, the element label and its source usually disambiguate it. Ask the human only when…
  4. Verify in the app, do not eyeball it. Re-drive the affected control with reticle_act_and_wait and name the consequence, or reticle_look {…
  5. Resolve it

What it can do on your machine

Read from SKILL.md and the folder at commit 178e5c0. 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

    Shell commands in SKILL.md call:

    • npx
    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • docs.reticle.sh

    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

Fix What I Pointed At loads about 878 tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 397 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~878

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 reticlehq/reticle at commit 178e5c0, republished under its Apache-2.0 licence (© reticlehq). 397 words, ~878 tokens.

Download SKILL.mdSave it as .claude/skills/fix-what-i-pointed-at/SKILL.md (or your agent's skills folder).
name
fix-what-i-pointed-at
description
Pick up the bugs a human flagged by pointing at them in the running app, each arriving with the element, the note they typed, and the source file and line. Use when the user says they marked or flagged something, when starting a session on an app someone has been clicking through, when a designer or PM has left feedback in the UI, or when the user describes a problem as "that button there" without saying which file.
license
Apache-2.0
metadata.version
3.7.0
metadata.homepage
https://www.reticle.sh
metadata.repository
https://github.com/reticlehq/reticle

The human pointed at the bug. Go fix it.

"The spacing on that card is wrong" is unactionable in chat and precise in the app. Reticle's running app has a Flag a bug control: the human clicks it, points at an element, and types what is wrong. Each flag becomes a mark carrying the element, the note, and the file:line, so the round trip that usually costs a screenshot, a description, and two clarifying questions costs one call.

Not installed? RETICLE_INSTALL_SOURCE=npx_skill npx @reticlehq/server@latest init, then the install-and-verify skill.

Drain the marks

reticle_session({ action: "review", sessionId })
json
{
  "marks": [
    {
      "id": "m1",
      "note": "this button is misaligned",
      "label": "button \"Pay\"",
      "source": { "file": "src/Checkout.tsx", "line": 42 },
      "fix": "Open src/Checkout.tsx:42 and fix: this button is misaligned."
    }
  ],
  "pendingCount": 1
}

Check this at the start of a session, and again whenever the human has been in the app. Reading never consumes a mark, so list → fix → verify → resolve is safe to run in any order.

The loop

  1. Read the marks. Group them if several point at the same file: one edit often answers three.
  2. Open source.file at source.line. This is the whole point: no hunting for which component rendered that button.
  3. Fix what the note asks for. If the note is ambiguous, the element label and its source usually disambiguate it. Ask the human only when they genuinely do not.
  4. Verify in the app, do not eyeball it. Re-drive the affected control with reticle_act_and_wait and name the consequence, or reticle_look { action: "element" } on the element for a layout or theme complaint. A visual fix confirmed by looking at it is how the mark gets reopened.
  5. Resolve it:
reticle_session({ action: "review", sessionId, resolve: "m1" })

Resolve only after the fix is verified. A resolved mark is a promise to the human that the thing they pointed at is done.

Show full SKILL.md (130 more words)Show less

When you cannot fix one

Say so against that mark and leave it unresolved. A mark silently dropped is worse than an open one: the human believes it was handled and finds out later. If the note describes intended behaviour rather than a bug, say that too, and let them decide.

Report back in their vocabulary

They pointed at "that button". Report on "the Pay button on checkout", with what you changed and the evidence it now works. Marks come from people who are looking at the screen, not at the repo, so a report full of file paths and no user-facing language answers the wrong question.


Everything else: curl https://docs.reticle.sh/llms.txt. If a mark arrived without a usable source pointer, that is worth a reticle_session { action: "feedback" } with kind: "gap".

© reticlehq, Apache-2.0. 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 skills/fix-what-i-pointed-at of reticlehq/reticle.

Open the folder on GitHubat commit 178e5c0

Compare with similar skills

Fix What I Pointed At 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.

Fix What I Pointed At compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fix What I Pointed At this skillreticlehq/reticle1.2k—~878Automated safety check: PassApache-2.0
Codewhale Dogfood Installcodewhale-hq/Codewhale41k—~1.3kAutomated safety check: PassMIT
Issue Fixmono/SkiaSharp5.6k—~5.1kAutomated safety check: PassMIT
OpenROAD Issue TriageThe-OpenROAD-Project/OpenROAD3.2k—~842Automated safety check: PassBSD-3-Clause
Pre-Merge Checkjsmastery-pro/skills1.5k—~1.1kAutomated safety check: NotesMIT
Fix The Classjoetawil7/first-pass98—~1.5kAutomated safety check: PassMIT

Similar skills

  • Codewhale Dogfood Install

    codewhale-hq/Codewhale

    Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.

    41k GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Issue Fix

    mono/SkiaSharp

    Fix bugs in SkiaSharp C bindings. An agent skill from mono/SkiaSharp.

    5.6k GitHub stars~5.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • OpenROAD Issue Triage

    The-OpenROAD-Project/OpenROAD

    Reproduces an OpenROAD GitHub bug from an attached tarball and shrinks the failing design with whittle.py so maintainers get a minimal test case.

    3.2k GitHub stars~842 tokensUpdated today
    DevelopmentAuto-check passed
  • Pre-Merge Check

    jsmastery-pro/skills

    A gate before merge: verify runs the real app against the spec, and review has a different model do a senior code review, without editing code.

    1.5k GitHub stars~1.1k tokensUpdated 2 mo ago
    DevelopmentAuto-check: notes
  • Fix The Class

    joetawil7/first-pass

    Bug-fix routine that fixes the whole class of bug, not just the reported instance.

    98 GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Write The Docs

    supabase/supabase

    Official

    Draft new or updated Supabase docs content for a feature or launch, grounded in product intent (Linear when available), a read of the actual code, and the docs style guide.

    111k GitHub stars~3.9k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from reticlehq/reticle

All 19 skills in this repo
  • Agentic TDD

    reticlehq/reticle

    Applies red-green TDD to behavior unit tests cannot reach, by stating the expected outcome against the running app with Reticle before writing the feature.

    1.2k GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed
  • Whole-App Health Sweep

    reticlehq/reticle

    Sweeps a running web app by clicking every reachable control, then reports dead buttons, console errors, failed requests and mismatches between API data and the screen.

    1.2k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Broken UI Debugger

    reticlehq/reticle

    Finds why a running web app misbehaves when the console is empty and the code looks fine, by reading the click, request, store and console together.

    1.2k GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed
  • Drives and verifies Electron or Tauri desktop apps through Reticle, which sees the renderer and the IPC calls that a browser-based testing tool cannot observe.

    1.2k GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed
  • Finds out why a passing test suite sits on top of a broken app by comparing what the running app does with what the tests claim, using Reticle.

    1.2k GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Reticle Flow Replay

    reticlehq/reticle

    Saves a user journey driven through the app as a deterministic regression check that replays with no model and no test code, using Reticle.

    1.2k GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed

Questions about Fix What I Pointed At

What does Fix What I Pointed At do?

Picks up bugs a person flagged by pointing at elements in the running app, each mark carrying the element, their note and the source file and line, then fixes and verifies them. Reticle's running app has a Flag a bug control: a person clicks it, points at an element and types what is wrong. Each flag becomes a mark that carries the element, the note and a file and line pointer, so the usual cycle of screenshot, description and clarifying questions collapses into one call.

When should I use Fix What I Pointed At?

Fix What I Pointed At fits situations like: fixing bugs a designer or PM flagged directly in the running app; starting a session on an app someone has been clicking through; resolving a vague report like that button there without knowing the file.

How do I install Fix What I Pointed At in Claude Code?

Run `npx skills add reticlehq/reticle --skill fix-what-i-pointed-at -a claude-code`. Or copy the skill folder (skills/fix-what-i-pointed-at in reticlehq/reticle) into .claude/skills/fix-what-i-pointed-at in your project. Claude Code loads it when a task matches its description.

How do I install Fix What I Pointed At in Codex?

Run `npx skills add reticlehq/reticle --skill fix-what-i-pointed-at -a codex`. Or copy the skill folder (skills/fix-what-i-pointed-at in reticlehq/reticle) into .agents/skills/fix-what-i-pointed-at in your project. Codex loads it when a task matches its description.

Can I use Fix What I Pointed At 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 reticlehq/reticle --skill fix-what-i-pointed-at -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fix-what-i-pointed-at, .gemini/skills/fix-what-i-pointed-at, .github/skills/fix-what-i-pointed-at and .opencode/skills/fix-what-i-pointed-at in your project.

What does Fix What I Pointed At need to run?

Going by SKILL.md and its folder, Fix What I Pointed At needs the command-line tools its instructions call (npx and curl). Our summary lists: The Reticle server and a running app, installed with npx @reticlehq/server init.

Does Fix What I Pointed At access the network?

SKILL.md names 1 domain. In commands or code: docs.reticle.sh; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Fix What I Pointed At 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 Fix What I Pointed At use?

Fix What I Pointed At is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fix What I Pointed At use?

About 878 tokens (SKILL.md is roughly 3.5k 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 Fix What I Pointed At?

Skills that share tags, products or a category with Fix What I Pointed At: Codewhale Dogfood Install (codewhale-hq/Codewhale, 41k stars), Issue Fix (mono/SkiaSharp, 5.6k stars), OpenROAD Issue Triage (The-OpenROAD-Project/OpenROAD, 3.2k stars) and Pre-Merge Check (jsmastery-pro/skills, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fix What I Pointed At?

reticlehq (a GitHub organization) maintains it in reticlehq/reticle, which has 1,199 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 9, 2026.

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