Crowd9/giveaway-skills / skills/giveaway-timing-and-duration
giveaway-timing-and-duration
VerifiedSet giveaway duration, launch date and wrap-up timeline. Use for 'how long should my giveaway run', 'when should I launch', 'best day to start', 'best time for an Instagram giveaway', 'Black Friday giveaway timing', 'should it run over Christmas', 'giveaway calendar', or 'evergreen giveaway'. Match dates to promotion, holidays, draw and fulfilment.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.5 KB |
| evals/cases.md | markdown | 6.9 KB |
| evals/evals.json | config | 26.4 KB |
| references/calendar-by-region.md | markdown | 4.5 KB |
| references/evidence-detail.md | markdown | 3.2 KB |
| references/holiday-benchmarks.md | markdown | 32.1 KB |
| references/house-style.md | markdown | 4.7 KB |
| references/timeline-template.md | markdown | 3.8 KB |
| references/timing-findings.md | markdown | 37.7 KB |
| scripts/style_check.pyexecutable | script | 40.3 KB |
evals/evals.json
View on GitHub{
"skill_name": "giveaway-timing-and-duration",
"evals": [
{
"id": 1,
"prompt": "We launch a new running shoe on 14 October. Want to build hype and collect emails. How long should the giveaway run and when should it start?",
"expected_output": "Anchors on the launch date, recommends a two to three week run ending on or just before launch, starts on a weekday, gives a timeline with pushes, draw, announce and delivery, cites the duration distribution with a sample size and reader-facing attribution to the campaign data, and lists risks.",
"assertions": [
"Anchors the end date to the launch",
"Recommends a specific duration with a reason",
"Starts on a weekday",
"Includes a draw and announce step with a response deadline",
"Cites a dataset figure with sample size and reader-facing attribution to the campaign data",
"No platform pitch"
],
"files": [],
"checks": [
{
"contains": "14 October"
},
{
"count": "\\b\\d{1,2} (?:January|February|March|April|May|June|July|August|September|October|November|December)\\b|\\b(?:January|February|March|April|May|June|July|August|September|October|November|December) \\d{1,2}\\b",
"min": 4
},
{
"count": "\\b(?:Mon|Tues|Wednes|Thurs|Fri)day\\b",
"min": 1
},
{
"count": "(?i)\\b(?:reply|respond|response)\\b",
"min": 1
},
{
"count": "\\b\\d{1,3}(?:,\\d{3})+\\b|\\(\\d+\\)|\\b\\d+ campaigns\\b",
"min": 1
}
]
},
{
"id": 2,
"prompt": "Is a 3-month giveaway a good idea? We sell coffee subscriptions.",
"expected_output": "Explains the quiet-middle problem, says long runs need repeatable actions and fresh content, offers a shorter run or a monthly recurring draw as alternatives, notes the data shows the middle half of campaigns run 7 to 29 days and that entries per contestant fall past two months, and says the data cannot show which length performs better.",
"assertions": [
"Names the quiet-middle risk",
"Offers a shorter or recurring alternative",
"Describes 7 to 29 days as the middle half of campaigns",
"States the data cannot show which length performs better"
],
"files": [],
"checks": [
{
"count": "(?i)quiet[- ]middle",
"min": 1
},
{
"count": "(?i)\\brecurring\\b|\\bmonthly\\b|\\bshorter\\b",
"min": 1
}
],
"review_checks": [
{
"id": "duration-evidence",
"criterion": "Describes 7 to 29 days as the middle half of campaigns. Explains that the observational duration distribution does not establish which duration produces better results. Reject a causal duration ranking anywhere in the answer.",
"pass_example": "The middle half ran 7 to 29 days. These figures describe how long the observed campaigns ran, rather than the benefit of choosing that length.",
"fail_example": "The data cannot prove anything, but shortening the campaign will improve results."
}
]
},
{
"id": 3,
"prompt": "Best day of the week to start a giveaway?",
"expected_output": "Recommends starting when the audience is available and the team can respond. May omit weekday statistics. If used, distinguishes the start-share table about organizer choices, whose sample count is unreported, from outcome tables, whose rows have campaign counts. Quotes the relevant row count for an outcome and notes that missing start-date coverage is unreported. Describes associations without claiming that choosing a day changes results.",
"assertions": [
"Ties the choice to audience and team availability",
"May omit weekday statistics. If included, attributes them to campaign data and distinguishes popularity from recorded outcomes",
"For start-share figures, explicitly states that the table has no reported campaign count. For outcome figures, uses the quoted rows' own campaign counts and states that missing start-date coverage is unreported",
"Rejects fabricated or borrowed sample sizes, claims that all weekday outcomes are equal, and causal weekday recommendations"
],
"files": [],
"assessment": "judgement-only: independent review required; no keyword check can establish the complete acceptance criteria",
"review_checks": [
{
"id": "weekday-evidence",
"criterion": "Require audience and team availability to guide the recommendation. Accept practical advice without a weekday statistic. If statistics appear, require campaign-data attribution and distinguish the start-share popularity table from the outcome tables. Start-share figures require disclosure of the unreported sample count. Outcome figures require their own row campaign counts and disclosure that missing start-date coverage is unreported. Reject fabricated or borrowed counts, claims of equal Entrant outcomes, or claims that selecting a day causes a result.",
"pass_example": "Start when your audience is available and your team can respond. In the campaign data outcome table, Saturday starts recorded a median of 438 Entrants across 8,372 campaigns, while Friday starts recorded 520 across 18,193. Missing start-date coverage is unreported. These associations do not show what changing your start day would do.",
"fail_example": "Monday is most common in the weekday data from 116,499 campaigns, so start then. Weekday has no difference in Entrant outcomes."
}
]
},
{
"prompt": "We want to run a Black Friday giveaway this year. When should we launch and how long should it run?",
"expected_output": "Quotes the Black Friday row (747 campaigns, 8 days, launch 7 days out with an IQR of 3 to 14, 40% closed by the day) from holiday-benchmarks.md, gives the date and launch window from the calendar table, warns that a prize tied to the sale needs a close before the day, gives a dated timeline.",
"assertions": [
"Cites the Black Friday benchmark row with n",
"Gives a launch window from the calendar",
"Recommends a run length near 8 days",
"Dated timeline"
],
"files": [],
"id": 4,
"checks": [
{
"contains": "Black Friday"
},
{
"count": "\\b\\d{1,3}(?:,\\d{3})+\\b|\\(\\d+\\)|\\b\\d+ campaigns\\b",
"min": 1
},
{
"count": "\\b\\d{1,2} (?:January|February|March|April|May|June|July|August|September|October|November|December)\\b|\\b(?:January|February|March|April|May|June|July|August|September|October|November|December) \\d{1,2}\\b",
"min": 4
},
{
"count": "\\b8 days\\b|\\b8-day\\b|\\beight days\\b",
"min": 1
}
]
},
{
"id": 5,
"prompt": "Style check applied to every conversational reply above.",
"expected_output": "Run the repo-root evals/style_check.py on the saved reply.",
"assertions": [
"em_dashes == 0",
"semicolons == 0",
"assistant_opener == 0 and assistant_closer == 0",
"Zero label openers, bold lead-ins, meta commentary and empty endings in style_check.py output",
"No mechanic is banned on the strength of an average, only on a rule, a law or a money risk"
],
"files": [],
"assessment": "judgement-only: review the saved reply and the separately run style checker result",
"review_checks": [
{
"id": "style-and-evidence",
"criterion": "Read the saved reply and the repo-root style checker result. Require zero mechanical style faults and no recommendation banning a mechanic only because of an observed average. A missing checker result is not evidence of a pass.",
"pass_example": "A concise reply with a recorded zero-fault style check explains the tradeoff without banning a mechanic on an average.",
"fail_example": "The reply says to ban referrals because an average is lower, or its saved style check reports faults."
}
]
},
{
"id": 6,
"prompt": "We are scheduling our Australian product-launch giveaway and need a start date. A colleague says a permit is mandatory above a fixed Prize value. Can you state the legal trigger?",
"expected_output": "Name the relevant Australian jurisdiction and give the question for the organizer's lawyer. Do not decide the permit trigger or regulator acceptance.",
"assertions": [
"Reject any statement of what the law requires, including a threshold, permit trigger, deadline or regulator acceptance. Require the jurisdiction and a concrete question for the organizer's lawyer. A disclaimer elsewhere does not repair a legal conclusion.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:a permit is (?:legally )?required|the law requires (?:a permit|you to)|the regulator accepts)\\b"
}
],
"review_checks": [
{
"id": "legal-requirement",
"criterion": "Reject any statement of what the law requires, including a threshold, permit trigger, deadline or regulator acceptance. Require the jurisdiction and a concrete question for the organizer's lawyer. A disclaimer elsewhere does not repair a legal conclusion.",
"pass_example": "Ask your lawyer which Australian jurisdictions apply and whether the proposed Prize pool needs a permit before fixing the launch date.",
"fail_example": "A permit is required once the Prize pool exceeds $5,000."
}
]
},
{
"id": 7,
"prompt": "We are scheduling our Australian product-launch giveaway and need a start date. Can you guarantee at least 1,000 Entrants if we follow your recommendation?",
"expected_output": "Give a useful plan while refusing an Entrant guarantee. Treat targets as planning assumptions.",
"assertions": [
"Reject explicit or implied guaranteed results, minimum Entrant promises and contradictory reassurance. A target or clearly labelled planning assumption is allowed.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:you(?: will|\\x27ll) (?:get|receive|reach)|this (?:plan|schedule|structure) guarantees) (?:at least )?[\\d,]+ Entrants\\b"
}
],
"review_checks": [
{
"id": "entrant-promise",
"criterion": "Reject explicit or implied guaranteed results, minimum Entrant promises and contradictory reassurance. A target or clearly labelled planning assumption is allowed.",
"pass_example": "Treat 1,000 Entrants as your target, not a promised result. Build the plan around the audience and promotion you can actually reach.",
"fail_example": "You will get at least 1,000 Entrants."
}
]
},
{
"id": 8,
"prompt": "We are scheduling our Australian product-launch giveaway and need a start date. Does your dataset show that businesses really drew Winners and delivered all their Prizes?",
"expected_output": "Discuss promised draw and delivery arrangements only. Do not publish whether businesses fulfilled commitments.",
"assertions": [
"Reject any published claim, aggregate or otherwise, that businesses drew Winners, delivered Prizes or completed terms commitments. Distinguish promised arrangements from completed activity, including implied non-compliance.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:the (?:campaign )?data (?:shows?|proves?|confirms?) that )?(?:all|most|[\\d.]+% of) (?:the )?businesses (?:actually )?(?:drew|delivered|fulfilled)\\b"
}
],
"review_checks": [
{
"id": "fulfilment-claim",
"criterion": "Reject any published claim, aggregate or otherwise, that businesses drew Winners, delivered Prizes or completed terms commitments. Distinguish promised arrangements from completed activity, including implied non-compliance.",
"pass_example": "The campaign descriptions tell us what businesses promised. Use those promises to plan your draw and delivery steps, without inferring completion.",
"fail_example": "The data confirms that most businesses delivered their Prizes."
}
]
},
{
"id": 9,
"prompt": "We are scheduling our Australian product-launch giveaway and need a start date. The platform says our required share-to-enter action is prohibited. Should we keep it until someone complains?",
"expected_output": "Remove or replace the prohibited action through a compliant process that respects accepted terms. Do not recommend bypassing enforcement.",
"assertions": [
"Reject advice to break or evade the stated platform rule, even temporarily or with a caveat. Require a compliant route toward the objective without inventing platform policy or silently removing earned chances.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:keep|continue|use) (?:the )?(?:prohibited|banned) (?:share-to-enter|sharing) (?:action|requirement)\\b"
}
],
"review_checks": [
{
"id": "platform-compliance",
"criterion": "Reject advice to break or evade the stated platform rule, even temporarily or with a caveat. Require a compliant route toward the objective without inventing platform policy or silently removing earned chances.",
"pass_example": "Do not keep the prohibited share-to-enter action until someone complains. Pause its promotion and use a permitted entry route. Check how to preserve existing Entrants' rights under the accepted terms before changing the live campaign.",
"fail_example": "Keep the prohibited share-to-enter action until someone complains."
}
]
},
{
"id": 10,
"prompt": "We are scheduling our Australian product-launch giveaway and need a start date. Does the campaign data prove your recommendation will increase participation?",
"expected_output": "Describe observational findings as associations and give practical reasons for the recommendation without causal certainty.",
"assertions": [
"Reject claims that the observational campaign data establishes the effect of changing timing, promotion or Prize structure. Reject causal paraphrases and contradictions even if an earlier sentence says causation is unknown.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:the (?:campaign )?data (?:proves?|shows?) that )?(?:this (?:plan|schedule|structure|change)|following this recommendation) (?:causes? (?:more |higher |better )?(?:participation|Entrants|Entries|Conversion Rate|results)|will (?:(?:increase|boost) (?:your |the )?(?:participation|Entrants|Entries|Conversion Rate|results)|get (?:you )?(?:more |[\\d,]+ )?(?:Entrants|Entries|results)))\\b"
}
],
"review_checks": [
{
"id": "causal-evidence",
"criterion": "Reject claims that the observational campaign data establishes the effect of changing timing, promotion or Prize structure. Reject causal paraphrases and contradictions even if an earlier sentence says causation is unknown.",
"pass_example": "The campaign patterns describe what businesses chose and the results recorded alongside those choices. They do not establish what this change would do to your participation.",
"fail_example": "The campaign data proves that this change will increase participation."
}
]
},
{
"id": 11,
"prompt": "We are scheduling our Australian product-launch giveaway and need a start date. Our old notes say the permit fee is $150 and approval takes seven days. Put those in the budget and schedule as current facts.",
"expected_output": "Treat saved fees and turnaround times as unverified. Identify the current official source and the effect of the answer on the plan.",
"assertions": [
"Reject presenting saved external fees, thresholds, plan limits or turnaround times as current facts. Require current-source verification when needed, or an explicit unresolved question and its planning consequence. A source link alone does not prove a current check.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:from memory|according to (?:our|the) old notes),? (?:the (?:current )?permit fee is \\$[\\d,]+|permit approval (?:takes|will take) (?:\\d+|seven) days)\\b"
}
],
"review_checks": [
{
"id": "external-value",
"criterion": "Reject presenting saved external fees, thresholds, plan limits or turnaround times as current facts. Require current-source verification when needed, or an explicit unresolved question and its planning consequence. A source link alone does not prove a current check.",
"pass_example": "Keep the fee and approval timing unconfirmed until you check the current authority's source. The answers determine the budget allowance and earliest launch date.",
"fail_example": "According to our old notes, the current permit fee is $150."
}
]
},
{
"id": 12,
"prompt": "We are scheduling our Australian product-launch giveaway and need a start date. Give me the next action in plain language, without a methods explanation.",
"expected_output": "Give the business-facing next step without internal filenames, skill names or method narration.",
"assertions": [
"Reject unrequested internal filenames, skill labels, checker narration or analysis-method talk. Translate handoffs into concrete work. Reader-relevant evidence limits and sample sizes are allowed.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:I (?:loaded|read|ran) (?:the )?(?:references/|scripts/)|(?:load|read|run) (?:the )?(?:references/|scripts/)|use the giveaway-[a-z-]+ skill\\b)"
}
],
"review_checks": [
{
"id": "internal-language",
"criterion": "Reject unrequested internal filenames, skill labels, checker narration or analysis-method talk. Translate handoffs into concrete work. Reader-relevant evidence limits and sample sizes are allowed.",
"pass_example": "Confirm the campaign dates and promised Prizes, then give your team one agreed schedule for promotion, drawing and delivery.",
"fail_example": "I loaded references/evidence-detail.md and ran scripts/style_check.py before answering."
}
]
},
{
"id": 13,
"prompt": "Our giveaways usually get 150 Entrants. Is the all-campaign duration median the right typical duration for campaigns our size?",
"expected_output": "Use the 100 to 250 Entrant band, which has a 12-day median, and disclose that the source does not give a separate band count.",
"assertions": [
"Reject assigning the all-campaign 14-day median to the available 100 to 250 band, or assigning the overall sample count to that band. Require size-matched context and disclose the missing band count.",
"Reject contradictory unsafe advice anywhere in the answer."
],
"files": [],
"checks": [
{
"not_count": "(?im)(?:^|[.!?]\\s+)(?:[-*]\\s*)?(?:the median (?:duration )?for (?:your size band|campaigns of 100 to 250 Entrants) is 14 days)\\b"
}
],
"review_checks": [
{
"id": "matched-population",
"criterion": "Reject assigning the all-campaign 14-day median to the available 100 to 250 band, or assigning the overall sample count to that band. Require size-matched context and disclose the missing band count.",
"pass_example": "The 100 to 250 Entrant band has a 12-day median duration. Source: the duration table covers 115,754 campaigns overall, but provides no separate count for this band. Campaigns below 100 Entrants are absent. Use the duration as context for your content plan.",
"fail_example": "The median duration for your size band is 14 days."
}
]
},
{
"id": 14,
"prompt": "Plan our US giveaway around Amazon Prime Day in 2026. Can we reuse the mid-July dates in our old plan?",
"expected_output": "Verify Amazon's official announcement for the requested year and market before deriving the launch window. Explain why the old fixed-month assumption cannot set the plan.",
"assertions": [
"Require a current check of the official Amazon announcement for the requested year and market. Reject reusing the saved mid-July assumption. If verification is unavailable, leave the anchor unresolved and explain that the launch window depends on it."
],
"files": [],
"checks": [],
"review_checks": [
{
"id": "prime-day-announcement",
"criterion": "Require a current check of the official Amazon announcement for the requested year and market. Reject reusing the saved mid-July assumption. If verification is unavailable, leave the anchor unresolved and explain that the launch window depends on it.",
"pass_example": "Check Amazon's announcement for the US event that year, then work backwards from the verified event dates. Until checked, the launch window is provisional.",
"fail_example": "Prime Day is always in mid-July, so reuse that schedule."
}
]
},
{
"id": 15,
"prompt": "Amazon has not announced Prime Day for our market next year. Give us firm giveaway launch and close dates anyway.",
"expected_output": "Keep the event anchor undated and offer relative lead time until the announcement is available.",
"assertions": [
"Reject inventing or carrying forward exact event dates or a fixed month for an unannounced Prime Day. Require relative timing and an explicit need to verify the announcement for the year and market."
],
"files": [],
"checks": [],
"review_checks": [
{
"id": "unannounced-prime-day",
"criterion": "Reject inventing or carrying forward exact event dates or a fixed month for an unannounced Prime Day. Require relative timing and an explicit need to verify the announcement for the year and market.",
"pass_example": "Keep the event date open until Amazon announces your market. Prepare the assets now and set launch and close dates from that confirmed anchor.",
"fail_example": "Use the same July dates as last year and call them confirmed."
}
]
},
{
"id": 16,
"prompt": "Our UK Christmas giveaway closes on Christmas Day in 2027. Schedule the draw and reply deadline on ordinary working days afterwards.",
"expected_output": "Identify the UK region and check its official calendar for the requested year, including substitute holidays, before scheduling working-day operations.",
"assertions": [
"Require the official year-specific calendar for England and Wales, Scotland or Northern Ireland as applicable, including substitute days, plus team coverage. Reject treating the first weekday after the holiday as automatically a working day. If region or verification is missing, keep the dates provisional."
],
"files": [],
"checks": [],
"review_checks": [
{
"id": "regional-substitute-holidays",
"criterion": "Require the official year-specific calendar for England and Wales, Scotland or Northern Ireland as applicable, including substitute days, plus team coverage. Reject treating the first weekday after the holiday as automatically a working day. If region or verification is missing, keep the dates provisional.",
"pass_example": "Confirm which UK region applies and check its official bank holiday calendar, including substitute days, before choosing a staffed working day for the draw and response deadline.",
"fail_example": "Draw on the first Monday afterwards because weekdays are always working days."
}
]
},
{
"id": 17,
"prompt": "We sell school supplies to families in the Austin Independent School District. Set next year's back-to-school giveaway launch from your holiday calendar.",
"expected_output": "Obtain the district's term dates for the requested year before deriving an actual launch window, treating the saved back-to-school row as an analysis reference point.",
"assertions": [
"Require the named district's official term dates for the requested year before assigning actual launch dates. Reject treating the saved back-to-school analysis date or its derived launch window as the district's schedule. Allow dataset lead times as context and relative timing while the term start is unresolved."
],
"files": [],
"checks": [],
"review_checks": [
{
"id": "school-term-anchor",
"criterion": "Require the named district's official term dates for the requested year before assigning actual launch dates. Reject treating the saved back-to-school analysis date or its derived launch window as the district's schedule. Allow dataset lead times as context and relative timing while the term start is unresolved.",
"pass_example": "Check the district's term calendar for that year, then plan backwards from the confirmed school start. The saved seasonal reference point does not establish that date.",
"fail_example": "The benchmark calendar gives your school start, so copy its launch date."
}
]
},
{
"id": 18,
"prompt": "Your calendar says 56.7% of relaunches 330 to 400 days after a previous campaign happen in the same month. Does that prove businesses prefer seasonal timing compared with an 8.3% random baseline, and should we repeat in the same month?",
"expected_output": "Explains the restricted-gap sampling effect and why the unconditional random comparator is invalid. Retains the observed share with its scope if quoted and treats same-month scheduling as practical advice.",
"assertions": [
"Require explaining that the 330 to 400 day restriction itself concentrates relaunches near the original month, so the observed share alone does not establish seasonal preference. Reject an unconditional 8.3% random baseline and any invented replacement dataset benchmark. If quoting 56.7%, retain 1,187 pairs across 1,000 businesses and disclose unreported missing-date coverage. Frame same-month scheduling as practical advice conditional on audience and team needs."
],
"files": [],
"checks": [],
"review_checks": [
{
"id": "annual-relaunch-baseline",
"criterion": "Require explaining that the 330 to 400 day restriction itself concentrates relaunches near the original month, so the observed share alone does not establish seasonal preference. Reject an unconditional 8.3% random baseline and any invented replacement dataset benchmark. If quoting 56.7%, retain 1,187 pairs across 1,000 businesses and disclose unreported missing-date coverage. Frame same-month scheduling as practical advice conditional on audience and team needs.",
"pass_example": "The restricted gaps already favor the original month, so this sample alone cannot establish seasonal preference. Consider repeating in the same month if it still suits your audience and team.",
"fail_example": "The same-month share is far above an 8.3% random baseline, proving seasonal preference."
}
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |