Agent skill

Lockedin Render Ideas

by daypunk in daypunk/LockedIn

Proposes 3 to 5 next-project or career-move ideas grounded in the user's experience.

MITAuto-check passedEducation

Install Lockedin Render Ideas

skills CLI
$ npx skills add daypunk/LockedIn --skill lockedin-render-ideas -a claude-code

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

GitHub CLI
$ gh skill install daypunk/LockedIn lockedin-render-ideas --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/daypunk/LockedIn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/lockedin/skills/lockedin-render-ideas .claude/skills/lockedin-render-ideas && 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
lockedin-render-ideas
GitHub stars
128
Token cost
~661 tokens
SKILL.md length
244 words
Files
6
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Proposes 3 to 5 next-project or career-move ideas grounded in the user's experience.

  • Says <!-- ko-example --what should I work on next
  • SKILL.md covers Use this when, Do NOT use when, Two-turn pattern and Output shape, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Side project ideas

What it does

Lockedin Render Ideas is an agent skill from daypunk/LockedIn. Proposes 3 to 5 next-project or career-move ideas grounded in the user's experience. One-paragraph pitch each, with cited entities. Two-turn writer/reviewer with a 5-dimension rubric. Activate when the user says <!-- ko-example --"what should I work on next", "side project ideas", "새 프로젝트 아이디어", "career pivot ideas"<!-- /ko-example --.

Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `RUBRIC.md`, `banned_phrases.json` and `prompt-reviewer.md`).

It sits in Education, covering Quizzes and assessments. The repository describes itself as: Lives inside your Claude Code session. Capture work as structured experience, then render resumes, Korean cover letters, interview answers, and project ideas from it. The licence is MIT.

When your agent uses it

  • Says <!-- ko-example --what should I work on next
  • Side project ideas
  • Career pivot ideas<!-- /ko-example --

Example prompts

  • “what should I work on next”
  • “side project ideas”
  • “career pivot ideas”
  • “/lockedin-render-ideas”

What it can do on your machine

Read from SKILL.md and the folder at commit 02d8766. 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

Lockedin Render Ideas loads about 661 tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 244 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~661

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 daypunk/LockedIn at commit 02d8766, republished under its MIT licence (© daypunk). 244 words, ~661 tokens.

Download SKILL.mdSave it as .claude/skills/lockedin-render-ideas/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
lockedin-render-ideas
description
Proposes 3 to 5 next-project or career-move ideas grounded in the user's experience. One-paragraph pitch each, with cited entities. Two-turn writer/reviewer with a 5-dimension rubric. Activate when the user says <!-- ko-example -->"what should I work on next", "side project ideas", "새 프로젝트 아이디어", "career pivot ideas"<!-- /ko-example -->.

render-ideas

Status: v1.2 (calibrated). Research-based calibration complete. RUBRIC.md ships with five cross-source-validated dimensions. A banned_phrases.json (27 entries, each backed by 2+ sources) and research-notes.md (7 cited sources) ship alongside the prompts. Pass/fail fixture corpus under tests/fixtures/ideas/.

Use this when

  • The user asks "what should I work on next" or "ideas for side projects" or names a constraint and asks for proposals.
  • The user wants to surface novel combinations of their existing skills and domains.
  • The user asks for career-move pitches grounded in their actual experience.

Do NOT use when

  • The user wants a resume or cover letter → render-resume-en / render-jaso.
  • The user wants an interview answer → render-interview.
  • The vault is sparse. Seed first via /lockedin init or ingestion.

Two-turn pattern

Writer turn surfaces 3 to 5 ideas. Reviewer turn re-loads RUBRIC.md fresh and scores the set on five dimensions.

Output shape

3 to 5 ideas, each one paragraph long, with a one-sentence pitch followed by two to three sentences of rationale that cite vault entities. Slug citations ([[type/slug]]) are resolved to natural language by the orchestrator before the user sees the artifact.

Files in this directory

SKILL.md             (this file)
research-notes.md    7 cited sources, cross-source analysis summary
banned_phrases.json  27 entries, severity-tagged, each backed by 2+ URLs
prompt-writer.md     writer-turn instruction
prompt-reviewer.md   reviewer-turn instruction (re-loads RUBRIC.md fresh)
RUBRIC.md            5-dimension scoring contract + score bands

Calibration status

v1.2 calibrated. The rubric dimensions (feasibility, novelty, evidence_ground, scope_match, motivation_alignment) are grounded in cross-source public research from Atlassian, Inc., FasterCapital, Proposify, Built In, fundsforNGOs, and arXiv. The banned_phrases.json contains 27 entries across five categories (buzzword_opener, vague_enthusiasm, hedging_language, unsubstantiated_claim, comparison_shortcut), each backed by 2+ independent sources. Pass and fail fixture corpus is at tests/fixtures/ideas/{pass,fail}/ (3 pass, 3 fail).

© daypunk, 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 5 other files in plugins/lockedin/skills/lockedin-render-ideas of daypunk/LockedIn.

  • SKILL.md
  • RUBRIC.md
  • banned_phrases.json
  • prompt-reviewer.md
  • prompt-writer.md
  • research-notes.md

Open the folder on GitHubat commit 02d8766

Compare with similar skills

Lockedin Render Ideas 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.

Lockedin Render Ideas compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lockedin Render Ideas this skilldaypunk/LockedIn128—~661Automated safety check: PassMIT
Agentsop Module Shape Selectionagentsope/SkillAlchemy466—~4.3kAutomated safety check: PassMIT
Evaluator CalibrationArchive228/loopkit755—~1.1kAutomated safety check: PassMIT
Agent Hiring Panelmohitagw15856/pm-claude-skills1.4k—~1.4kAutomated safety check: PassMIT
Expense Disciplinemohitagw15856/pm-claude-skills1.4k—~1.5kAutomated safety check: PassMIT
Role Redesign For AImohitagw15856/pm-claude-skills1.4k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Agentsop Module Shape Selection

    agentsope/SkillAlchemy

    ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer.

    466 GitHub stars~4.3k tokensUpdated today
    EducationAuto-check passed
  • Evaluator Calibration

    Archive228/loopkit

    Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.

    755 GitHub stars~1.1k tokensUpdated 2 mo ago
    EducationAuto-check passed
  • Agent Hiring Panel

    mohitagw15856/pm-claude-skills

    Hire an AI agent the way you'd hire an employee — a role spec with success criteria, a structured work-sample interview run on your real tasks, reference checks (what do actual users report)…

    1.4k GitHub stars~1.4k tokensUpdated yesterday
    EducationAuto-check passed
  • Expense Discipline

    mohitagw15856/pm-claude-skills

    Submit expenses that sail through approval — the capture-at-spend habit, the policy-fluency that prevents rejections (thresholds, receipt rules, the pre-approval traps), the report assembled in…

    1.4k GitHub stars~1.5k tokensUpdated yesterday
    EducationAuto-check passed
  • Role Redesign For AI

    mohitagw15856/pm-claude-skills

    Redesign a job role that AI now does a large part of — deliberately, instead of quietly expecting the same headcount to absorb 140% output.

    1.4k GitHub stars~1.6k tokensUpdated yesterday
    EducationAuto-check passed
  • Interview Kit Builder

    w95/awesome-claude-corporate-skills

    TRIGGER THIS when preparing interviews, planning hiring processes, creating interview questions, building evaluation frameworks, developing interviewer guides, or standardizing interview approaches.

    239 GitHub stars~3.7k tokensUpdated 7 mo ago
    EducationAuto-check passed

More from daypunk/LockedIn

  • Lockedin Audit

    daypunk/LockedIn

    Scores any resume or cover letter against LockedIn's calibrated rubric.

    128 GitHub stars~1.8k tokensUpdated 4 mo ago
    Auto-check passed
  • Drafts an interview answer in English or Korean from the user's experience.

    128 GitHub stars~728 tokensUpdated 4 mo ago
    Auto-check passed
  • Lockedin Render Jaso

    daypunk/LockedIn

    Writes a Korean 자기소개서 from the user's experience. An agent skill from daypunk/LockedIn.

    128 GitHub stars~701 tokensUpdated 4 mo ago
    Auto-check passed
  • Lockedin Capture

    daypunk/LockedIn

    Converts in-session capture intents ("save this", "log this", "track this", "absorb this") into structured vault entries via a two-turn writer/reviewer pattern with duplicate detection and…

    128 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check: warnings
  • Writes an English resume from the user's experience, tuned to one of 10 built-in personas.

    128 GitHub stars~884 tokensUpdated 4 mo ago
    Auto-check passed
  • Lockedin

    daypunk/LockedIn

    Captures the user's work moments — a shipped feature, a meeting outcome, a learning, a decision — from inside their Claude Code session into structured local markdown.

    128 GitHub stars~3.2k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Lockedin Render Ideas

What does Lockedin Render Ideas do?

Proposes 3 to 5 next-project or career-move ideas grounded in the user's experience. Lockedin Render Ideas is an agent skill from daypunk/LockedIn. Proposes 3 to 5 next-project or career-move ideas grounded in the user's experience.

When should I use Lockedin Render Ideas?

Lockedin Render Ideas fits situations like: says <!-- ko-example --what should I work on next; side project ideas; career pivot ideas<!-- /ko-example --.

How do I install Lockedin Render Ideas in Claude Code?

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

How do I install Lockedin Render Ideas in Codex?

Run `npx skills add daypunk/LockedIn --skill lockedin-render-ideas -a codex`. Or copy the skill folder (plugins/lockedin/skills/lockedin-render-ideas in daypunk/LockedIn) into .agents/skills/lockedin-render-ideas in your project. Codex loads it when a task matches its description.

Can I use Lockedin Render Ideas 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 daypunk/LockedIn --skill lockedin-render-ideas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lockedin-render-ideas, .gemini/skills/lockedin-render-ideas, .github/skills/lockedin-render-ideas and .opencode/skills/lockedin-render-ideas in your project.

What does Lockedin Render Ideas need to run?

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

Does Lockedin Render Ideas 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 Lockedin Render Ideas 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 Lockedin Render Ideas use?

Lockedin Render Ideas 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 Lockedin Render Ideas use?

About 661 tokens (SKILL.md is roughly 2.6k 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 Lockedin Render Ideas?

Skills that share tags, products or a category with Lockedin Render Ideas: Agentsop Module Shape Selection (agentsope/SkillAlchemy, 466 stars), Evaluator Calibration (Archive228/loopkit, 755 stars), Agent Hiring Panel (mohitagw15856/pm-claude-skills, 1.4k stars) and Expense Discipline (mohitagw15856/pm-claude-skills, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lockedin Render Ideas?

daypunk (a GitHub user) maintains it in daypunk/LockedIn, which has 128 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on May 22, 2026.

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