Agent skill

Decision When Tired

by mohitagw15856 in mohitagw15856/pm-claude-skills

Make a decent decision when you're too depleted to think well — a low-energy protocol that protects you from bad tired-brain choices.

MITAuto-check passed

Install Decision When Tired

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill decision-when-tired -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills decision-when-tired --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/decision-when-tired .claude/skills/decision-when-tired && 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
decision-when-tired
GitHub stars
1.4k
Token cost
~1k tokens
SKILL.md length
507 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Make a decent decision when you're too depleted to think well — a low-energy protocol that protects you from bad tired-brain choices.

  • Works in 5 steps: Ask if it can wait. The strongest move… → Flag the tired traps. Name how… → Favor reversible. If a choice must be… → …
  • Asked Im too tired to decide
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: First, Don't Decide and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Decision When Tired is an agent skill from mohitagw15856/pm-claude-skills. Make a decent decision when you're too depleted to think well — a low-energy protocol that protects you from bad tired-brain choices. Use when asked I'm too tired to decide, help me choose I'm exhausted, I can't think straight right now, or should I even decide this now. Produces a first check on whether this decision can simply wait until you're rested, and if not, a minimal-effort path to a safe-enough choice (default to reversible, avoid the tired-brain traps, use a simple rule) — because decisions made…

Its SKILL.md is about 1k 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: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked Im too tired to decide
  • Help me choose Im exhausted
  • I cant think straight right now
  • Should I even decide this now

Example prompts

  • “m too tired to decide, help me choose I”
  • “/decision-when-tired”

Workflow steps

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

  1. Ask if it can wait. The strongest move is usually to defer — most "urgent" decisions can survive until morning. Push hard on this first.
  2. Flag the tired traps. Name how exhaustion is likely skewing this — toward the impulsive, the pessimistic, or the…
  3. Favor reversible. If a choice must be made now, bias hard toward the option you can undo — it caps the downside of a bad tired call.
  4. Satisfice, don't optimize. Good-enough beats perfect when you can't think clearly; use a simple rule, not deep analysis.
  5. Protect the big ones. Explicitly refuse to make major, irreversible decisions while depleted — put them on the do-not-decide-now list.

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

Decision When Tired loads about 1k tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 507 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~153
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 507 words, ~1,025 tokens.

Download SKILL.mdSave it as .claude/skills/decision-when-tired/SKILL.md (or your agent's skills folder).
name
decision-when-tired
description
Make a decent decision when you're too depleted to think well — a low-energy protocol that protects you from bad tired-brain choices. Use when asked I'm too tired to decide, help me choose I'm exhausted, I can't think straight right now, or should I even decide this now. Produces a first check on whether this decision can simply wait until you're rested, and if not, a minimal-effort path to a safe-enough choice (default to reversible, avoid the tired-brain traps, use a simple rule) — because decisions made depleted are predictably worse, and the best move is often not to make them now.

Decision When Tired

Tired brains make bad decisions — impulsive, pessimistic, or whatever's easiest — and then live with them. The best protocol when depleted is usually don't decide yet. This first checks whether the decision can wait; if it genuinely can't, it walks you to a safe-enough choice with minimal thinking: default to the reversible option, dodge the known tired-brain traps, and apply a simple rule rather than deep analysis you can't do right now.

What This Skill Produces

  • The can-it-wait check — the first and best question: does this actually need deciding now, or can it wait for a rested brain?
  • The tired-brain trap flags — the predictable ways exhaustion distorts choices (impulse-buying, catastrophizing, picking the easy-not-right option, saying yes to make it stop)
  • The safe-enough path — if it can't wait, a low-effort route to a reasonable choice (favor reversible, satisfice, use a rule)
  • A simple decision rule — a heuristic to apply instead of analysis you don't have the energy for
  • A do-not-decide list — the choices to explicitly defer until rested

Required Inputs

Ask for these if not provided:

  • The decision — what you're trying to choose
  • The real deadline — does it truly need deciding now, or does it just feel that way
  • How depleted you are — mildly tired or completely fried
  • Reversibility — can the choice be undone or changed later

Framework: First, Don't Decide

  1. Ask if it can wait. The strongest move is usually to defer — most "urgent" decisions can survive until morning. Push hard on this first.
  2. Flag the tired traps. Name how exhaustion is likely skewing this — toward the impulsive, the pessimistic, or the easiest-to-end-the-discomfort option.
  3. Favor reversible. If a choice must be made now, bias hard toward the option you can undo — it caps the downside of a bad tired call.
  4. Satisfice, don't optimize. Good-enough beats perfect when you can't think clearly; use a simple rule, not deep analysis.
  5. Protect the big ones. Explicitly refuse to make major, irreversible decisions while depleted — put them on the do-not-decide-now list.
Show full SKILL.md (173 more words)Show less

Output Format

Decision: [what you're choosing] · depletion: [level]

Can it wait? [yes → defer to when rested: that's the answer] / [no → continue]. Tired-brain traps right now: [impulse / catastrophizing / easy-not-right / yes-to-end-it]. If you must choose now: favor [the reversible option] · apply this rule: [simple heuristic]. Do NOT decide tonight: [any big/irreversible choices → wait].

Quality Checks

  • Leads with "can this wait?" as the primary move
  • Flags the specific tired-brain distortions at play
  • Biases toward reversible options if a choice is forced
  • Offers a simple rule instead of demanding analysis
  • Explicitly defers major/irreversible decisions

Anti-Patterns

  • Demanding careful analysis from a fried brain.
  • Not offering the "just wait" option first.
  • Letting a big irreversible choice get made while depleted.
  • Ignoring how exhaustion is skewing the choice.

Example Trigger Phrases

  • "I'm exhausted and need to decide something — help."
  • "Should I even make this decision tonight?"
  • "I can't think straight but I have to choose. Help me not mess it up."
  • "I'm fried — is this a decide-now or a decide-later?"
  • "Help me pick something safe, I'm too tired to think."

© mohitagw15856, 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 skills/decision-when-tired of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Decision When Tired 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.

Decision When Tired compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Decision When Tired this skillmohitagw15856/pm-claude-skills1.4k—~1kAutomated safety check: PassMIT
Manual CLI Testpigweed-project/pigweed548—~4.1kAutomated safety check: PassApache-2.0
Technical Writing Standardcursor/plugins11k10 repos~2.3kAutomated safety check: PassNone
Co Tank Monitoraipoch/medical-research-skills1.9k—~1.8kAutomated safety check: PassMIT
Lab Inventory Predictoraipoch/medical-research-skills1.9k—~2.2kAutomated safety check: PassMIT
Bio Ribo Seq Riboseq PreprocessingGPTomics/bioSkills1.2k1 repos~3.6kAutomated safety check: PassMIT

Similar skills

  • Manual CLI Test

    pigweed-project/pigweed

    Interactively "taste the CLI" and "kick the tires" on any CLI tool or subcommand (/manual-cli-test, /agent-cli-kick-tires).

    548 GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    11k GitHub starsUsed in 10 repos~2.3k tokens
    Writing & ContentAuto-check passed
  • Co Tank Monitor

    aipoch/medical-research-skills

    IoT monitoring simulation to predict CO2 tank depletion and prevent weekend gas outages in cell culture facilities.

    1.9k GitHub stars~1.8k tokensUpdated 24 days ago
    Productivity & AutomationAuto-check passed
  • Lab Inventory Predictor

    aipoch/medical-research-skills

    Predict depletion time of critical lab reagents based on historical usage frequency, and automatically generate purchase alerts when stock falls below safety thresholds.

    1.9k GitHub stars~2.2k tokensUpdated 24 days ago
    Auto-check passed
  • Preprocess ribosome profiling reads with UMI handling, adapter trimming, contaminant/rRNA depletion, and footprint-aware alignment.

    1.2k GitHub starsUsed in 1 repo~3.6k tokens
    Writing & ContentAuto-check passed
  • Oopsla Artifact Evaluation

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when packaging an artifact for an accepted OOPSLA paper under the SPLASH artifact-evaluation track — surviving the kick-the-tires phase, earning the Functional and Reusable…

    1.2k GitHub stars~1.1k tokensUpdated 14 days ago
    Auto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Decision When Tired

What does Decision When Tired do?

Make a decent decision when you're too depleted to think well — a low-energy protocol that protects you from bad tired-brain choices. Decision When Tired is an agent skill from mohitagw15856/pm-claude-skills. Make a decent decision when you're too depleted to think well — a low-energy protocol that protects you from bad tired-brain choices.

When should I use Decision When Tired?

Decision When Tired fits situations like: asked Im too tired to decide; help me choose Im exhausted; I cant think straight right now; should I even decide this now.

How do I install Decision When Tired in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill decision-when-tired -a claude-code`. Or copy the skill folder (skills/decision-when-tired in mohitagw15856/pm-claude-skills) into .claude/skills/decision-when-tired in your project. Claude Code loads it when a task matches its description.

How do I install Decision When Tired in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill decision-when-tired -a codex`. Or copy the skill folder (skills/decision-when-tired in mohitagw15856/pm-claude-skills) into .agents/skills/decision-when-tired in your project. Codex loads it when a task matches its description.

Can I use Decision When Tired 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 mohitagw15856/pm-claude-skills --skill decision-when-tired -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/decision-when-tired, .gemini/skills/decision-when-tired, .github/skills/decision-when-tired and .opencode/skills/decision-when-tired in your project.

What does Decision When Tired need to run?

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

Does Decision When Tired 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 Decision When Tired 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 Decision When Tired use?

Decision When Tired 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 Decision When Tired use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Decision When Tired?

Skills that share tags, products or a category with Decision When Tired: Manual CLI Test (pigweed-project/pigweed, 548 stars), Technical Writing Standard (cursor/plugins, 11k stars), Co Tank Monitor (aipoch/medical-research-skills, 1.9k stars) and Lab Inventory Predictor (aipoch/medical-research-skills, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Decision When Tired?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.